Papers › Proximal Policy Optimization Algorithms
Proximal Policy Optimization Algorithms
John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, Oleg Klimov
We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent. Whereas standard policy gradient methods perform one gradient update per data sample, we propose a novel objective function that enables multiple epochs of minibatch updates. The new methods, which we call proximal policy optimization (PPO), have some of the benefits of trust region policy optimization (TRPO), but they are much simpler to implement, more general, and have better sample complexity (empirically). Our experiments test PPO on a collection of benchmark tasks, including simulated robotic locomotion and Atari game playing, and we show that PPO outperforms other online policy gradient methods, and overall strikes a favorable balance between sample complexity, simplicity, and wall-time.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="1707.06347")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1707.06347", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1707.06347")
Code
Syntology 176 code samples: 173 from 64 repositories linked to this paper, 3 identical to code harvested from another paper's repository. Across all 176: 99 ran (of which 53 constructed an object rather than computing a result; 71 with no instrument failure: 7 honoured, 2 violated, 62 with no contract checked; 28 where Syntology's instrument failed) · 77 unverified. Where Syntology's instrument failed: 27 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 173 samples from 64 repositories, 96 ran (69 with no instrument failure; 27 where Syntology's instrument failed); 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
No sample is linked to this paper from 26 of its repositories that Syntology harvested for other papers:
- Crevass/Hybrid-Agent, community (archive-listed): harvested for another paper, listed under the repository
- ailab-pku/rl-framework, community (archive-listed): harvested for another paper, listed under the repository
- alex-petrenko/sample-factory, community (archive-listed): harvested for another paper, listed under the repository
- alirezakazemipour/ppo-rnd, community (archive-listed): harvested for another paper, listed under the repository
- araffin/sbx, community (archive-listed): harvested for another paper, listed under the repository
- automl/learna, community (archive-listed): harvested for another paper, listed under the repository
- bentrevett/pytorch-rl, community (archive-listed): harvested for another paper, listed under the repository
- chainer/chainerrl, community (archive-listed): harvested for another paper, listed under the repository
- deconlabs/Binanace-trading-simulation, community (archive-listed): harvested for another paper, listed under the repository
- emerge-lab/nocturne_lab, community (archive-listed): harvested for another paper, listed under the repository
- fdcl-gwu/gym-rotor, community (archive-listed): harvested for another paper, listed under the repository
- ikostrikov/pytorch-a2c-ppo-acktr-gail, community (archive-listed): harvested for another paper, listed under the repository
- inoryy/reaver, community (archive-listed): harvested for another paper, listed under the repository
- jcwleo/curiosity-driven-exploration-pytorch, community (archive-listed): harvested for another paper, listed under the repository
- jcwleo/random-network-distillation-pytorch, community (archive-listed): harvested for another paper, listed under the repository
- michael-snower/ppo, community (archive-listed): harvested for another paper, listed under the repository
- microsoft/strategically_efficient_rl, community (archive-listed): harvested for another paper, listed under the repository
- synthlabsai/big-math, community (archive-listed): harvested for another paper, listed under the repository
- tatsu-lab/linguistic_calibration, community (archive-listed): harvested for another paper, listed under the repository
- theresearchai/vehicle_routing_rl_2, community (archive-listed): harvested for another paper, listed under the repository
- tidedra/vl-rlhf, community (archive-listed): harvested for another paper, listed under the repository
- tmjeong1103/RL_with_RAY, community (archive-listed): harvested for another paper, listed under the repository
- DLR-RM/stable-baselines3, community (archive-listed): harvested for another paper, listed under the repository
- hill-a/stable-baselines, community (archive-listed): harvested for 2 other papers, listed under the repository
- labmlai/annotated_deep_learning_paper_implementations, community (archive-listed): harvested for 15 other papers, listed under the repository
- pytorch/rl, community (archive-listed): harvested for another paper, listed under the repository
Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 99 samples that ran have no recorded date.
188 repositories listed; official and paper-mentioned ones first.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
176 samples harvested: 99 ran (of which 53 constructed an object rather than computing a result; 71 with no instrument failure: 7 honoured, 2 violated, 62 with no contract checked; 28 where Syntology's instrument failed) · 77 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 94 of the 176 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 64 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. 3 samples are listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 13 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
bce2a8566fa36fda · report
088783306dda80fe · report
fixture: signature inputs:Tensor/2/float · returned tuple · level recorded 2026-09-22 be3a23c2176d855c · report
fixture: signature inputs:Tensor/2/float, deterministic:bool/0/bool · returned tuple · level recorded 2026-09-24 375f0073f16726f9 · report
fixture: signature m:callable/0/? · returned Linear · level recorded 2026-09-22 bb56e14071f60cba · report
fixture: signature x:Tensor/3/float · returned tuple · level recorded 2026-09-22 063d29364d7e4f81 · report
fixture: signature advantage:EagerTensor/2/float, old_prediction:EagerTensor/2/float · returned function · level recorded 2026-09-22 8e103b8cabd1203c · report
28919ed273c0c995 · report
fixture: returned DictList · level recorded 2026-09-22 06c62bb9eacfe08c · report
fixture: returned ExtraInfoCollector · level recorded 2026-09-22 f0b71d0c5374efdf · report
fixture: returned ParallelEnv · level recorded 2026-09-22 1cd2e751ff91ca44 · report
fixture: signature obss:list/1/list, device:NoneType/0/? · returned Tensor · level recorded 2026-09-22 6c7082241ec61d89 · report
dce583aa0f5fb136 · report
01571ae37dfefba2 · report
a5b8d69558cb1833 · report
fixture: signature mini_batch_size:int/0/int, data:ndarray/2/float, batch_index:int/0/int, flat:bool/0/bool, shape:NoneType/0/? · returned ndarray · level recorded 2026-09-22 7271dace2360dd93 · report
0b170016a5f01a6e · report
3e7bdf63d50d132e · report
c3cb4b39b7e82812 · report
fixture: returned Actor · level recorded 2026-09-22 5eac27c1ede5a3f1 · report
fixture: returned Buffer · level recorded 2026-09-22 f1685211d6effd06 · report
fixture: returned Critic · level recorded 2026-09-22 b46c632bedd3d8af · report
fixture: signature x:EagerTensor/2/float, mu:EagerTensor/2/float, log_std:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22 bf0c1da602f8a16d · report
708e869097ea91ff · report
cc0a6d60ba0d615d · report
fixture: returned Categorical · level recorded 2026-09-22 1e06bd08fb825800 · report
fixture: returned Continous · level recorded 2026-09-22 2492441b222787d6 · report
7f143a6ee276436b · report
fixture: returned ModelUpdate · level recorded 2026-09-22 b48c75c1f791937c · report
fixture: returned PPO · level recorded 2026-09-22 2eb0c930a45a7472 · report
fixture: returned PolicyUpdate · level recorded 2026-09-22 2c9a98eedcdea762 · report
df1fd605b67498ef · report
fixture: signature states:Tensor/2/float, actions:Tensor/2/float, log_probs:Tensor/2/float, returns:Tensor/2/float, advantage:Tensor/2/float · returned generator · level recorded 2026-09-22 f20ab80cf000ba69 · report
f8348c78f9a4c594 · report
fixture: signature policy:callable/0/?, states:list/1/Tensor · returned Tensor · level recorded 2026-09-22 db1820f47853260b · report
d196dcee4a5b1061 · report
c2f17acc73ce8ca9 · report
6ff581679958bf77 · report
fixture: signature state:Tensor/2/float, action:Tensor/1/int · returned tuple · level recorded 2026-09-22 d0735a6f70135e3f · report
fixture: signature transition:Transition/1/Tensor · returned Transition · level recorded 2026-09-22 e9f1207fc08f9fa9 · report
fixture: returned Actor · level recorded 2026-09-22 f7a59411ac390f78 · report
fixture: returned ActorCritic · level recorded 2026-09-22 b1f30e180cb81a3a · report
fixture: returned Agent · level recorded 2026-09-22 b4455ab1f545ae9c · report
fixture: returned Critic · level recorded 2026-09-22 8fc0ce07edd32744 · report
fixture: returned Actor · level recorded 2026-09-22 607bb439a428fd2a · report
fixture: returned ActorCritic · level recorded 2026-09-22 4c40cb5849fd342f · report
fixture: returned Agent · level recorded 2026-09-22 a7700bf49f384087 · report
fixture: signature model:callable/0/?, states:list/1/Tensor · returned Tensor · level recorded 2026-09-22 38803d98e366da6d · report
fixture: returned BaseAgent · level recorded 2026-09-22 6dbcf603fe9c4a6f · report
fixture: returned Batcher · level recorded 2026-09-22 e3bd893b00cce00e · report
fixture: returned PPOAgent · level recorded 2026-09-22 03b48449f3d4d675 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 a690a9a71794bce7 · report
c169652ebc3cb1c4 · report
fixture: returned RolloutBuffer · level recorded 2026-09-22 ab47bdba4f875268 · report
fixture: returned StateFunction · level recorded 2026-09-22 181b4202198be200 · report
fixture: returned StateIndependentPolicy · level recorded 2026-09-22 373bf1b3269456e9 · report
fixture: signature input_dim:int/0/int, output_dim:int/0/int, hidden_units:list/1/int, hidden_activation:callable/0/?, output_activation:callable/0/?, dropout:float/0/float · returned Sequential · level recorded 2026-09-22 92227b56b34a423b · report
fixture: signature means:Tensor/2/float, log_stds:Tensor/2/float, actions:Tensor/2/float · returned Tensor · level recorded 2026-09-22 527acc6b195e3ec9 · report
86201a6180de4a09 · report
6e26f9d72a957989 · report
fixture: returned PPO · level recorded 2026-09-22 58ee12a76b1fd1a1 · report
fixture: returned TrajectoryBuffer · level recorded 2026-09-22 census: 22 implementations from 25 papers, 16 distinct outputs across 4 buckets, one shared input per bucket src/jax_rl/algorithms/ppo.py ran · our draft was wrong fingerprinted MIT (permissive) ·
1732d17d766f28da · report
fixture: signature dist:ArrayImpl/2/float, axis:int/0/int · returned ArrayImpl · level recorded 2026-09-22 2dd687e050a61476 · report
6f2b092fd868a348 · report
6f986aa2d59a44f8 · report
fixture: returned RolloutBuffer_PPO_lag · level recorded 2026-09-22 a78ee4761e8df9d8 · report
fixture: returned StateFunction · level recorded 2026-09-22 fbd28096c7f0c30f · report
fixture: returned StateIndependentPolicy · level recorded 2026-09-22 census: 3 implementations from 5 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 Sources/algo/ppo.py ran · honoured contract no licence file found · pointer only ·
264c9e17d7dfe7eb · report
fixture: returned Tensor · level recorded 2026-09-22 c511268a73d82fc6 · report
fixture: returned Sequential · level recorded 2026-09-22 b5a22b5e0dce3796 · report
fixture: signature values:Tensor/1/float, rewards:Tensor/1/float, dones:Tensor/1/float, next_values:Tensor/1/float, gamma:float/0/float, lambd:float/0/float · returned tuple · level recorded 2026-09-22 77393baa1a11c24b · report
fixture: signature values:Tensor/1/float, rewards:Tensor/1/float, dones:Tensor/1/float, next_values:Tensor/1/float, gamma:float/0/float, lambd:float/0/float · returned tuple · level recorded 2026-09-22 476e14ee8b7219ac · report
fixture: signature log_stds:Tensor/2/float, noises:Tensor/2/float, actions:Tensor/2/float · returned Tensor · level recorded 2026-09-22 fef4ec37a6ea52e7 · report
fixture: signature means:Tensor/2/float, log_stds:Tensor/2/float, actions:Tensor/2/float · returned Tensor · level recorded 2026-09-22 census: 12 implementations from 17 papers, 5 distinct outputs across 4 buckets, one shared input per bucket Sources/algo/ppo.py ran · our draft was wrong fingerprinted no licence file found · pointer only ·
b1c9c127240c75d8 · report
fixture: signature means:Tensor/2/float, log_stds:Tensor/2/float · returned tuple · level recorded 2026-09-22 d5c516ed0fa589e3 · report
5dc5fc3b8ad0138c · report
786ef0f1e1c69fc2 · report
fixture: returned PPOAgent · level recorded 2026-09-22 7dbfda361c907b1e · report
fixture: signature state:Tensor/2/float, action:NoneType/0/? · returned dict · level recorded 2026-09-24 168b3d776129e246 · report
fixture: returned RolloutBuffer · level recorded 2026-09-22 7f9dae876ba7e00b · report
fixture: returned StateFunction · level recorded 2026-09-22 dea2715df3f6a1e3 · report
fixture: returned StateIndependentPolicy · level recorded 2026-09-22 b4f2ea8b3db73cea · report
fixture: signature log_stds:Tensor/2/float, noises:Tensor/2/float, actions:Tensor/2/float · returned Tensor · level recorded 2026-09-22 1cfc11023c8784d6 · report
fixture: signature means:Tensor/2/float, log_stds:Tensor/2/float, actions:Tensor/2/float · returned Tensor · level recorded 2026-09-22 census: 12 implementations from 17 papers, 5 distinct outputs across 4 buckets, one shared input per bucket gail_airl_ppo/algo/ppo.py ran · our draft was wrong fingerprinted MIT (permissive) ·
7c5e74bc668cf5cc · report
fixture: signature means:Tensor/2/float, log_stds:Tensor/2/float · returned tuple · level recorded 2026-09-22 2bddf6daaed4d669 · report
028cd0cc569e4945 · report
fixture: returned ParallelEnv · level recorded 2026-09-22 2f383d9f3f2f7b4f · report
fixture: signature x:Tensor/2/float · returned tuple · level recorded 2026-09-22 7539f57b4803c98e · report
fixture: returned ReplayMemory · level recorded 2026-09-22 ec594f35cdf2f00e · report
fixture: returned Policy · level recorded 2026-09-22 06f3c47cdf2dd979 · report
fixture: returned PolicyNN · level recorded 2026-09-22 54948e8edd9b8bc1 · report
fixture: signature unscaled_obs:list/1/ndarray, actions:list/1/ndarray, file_name:str/0/str · returned int · level recorded 2026-09-22 54ccb8ae3f658c83 · report
53db83baee745ffd · report
c004c93ba5634851 · report
f2a4b483cf41dcfd · report
fixture: returned MLP · level recorded 2026-09-22 1271c934496f2b53 · report
fixture: returned NormalizedMLP · level recorded 2026-09-22 049dd1dd7386f7f1 · report
fixture: returned RolloutBuffer · level recorded 2026-09-22 7e7afb47f6ebd451 · report
fixture: signature values:Tensor/1/float, rewards:Tensor/1/float, dones:Tensor/1/float, next_values:Tensor/1/float, gamma:float/0/float, lambd:float/0/float · returned tuple · level recorded 2026-09-22 eb4a6cb62afcb0ec · report
fixture: signature log_stds:Tensor/2/float, noises:Tensor/2/float, actions:Tensor/2/float · returned Tensor · level recorded 2026-09-22 c977657d1b1dadef · report
fixture: signature means:Tensor/2/float, log_stds:Tensor/2/float, actions:Tensor/2/float · returned Tensor · level recorded 2026-09-22 f2cddb5460e2bc7e · report
fixture: signature module:callable/0/?, gain:float/0/float · returned SimpleModule · level recorded 2026-09-22 census: 12 implementations from 17 papers, 5 distinct outputs across 4 buckets, one shared input per bucket neuriss/rl/ppo.py ran · our draft was wrong fingerprinted MIT (permissive) ·
6741967893f01eac · report
fixture: signature means:Tensor/2/float, log_stds:Tensor/2/float · returned tuple · level recorded 2026-09-22 08c8acc6b144eabd · report
fixture: returned PPOAlgorithm · level recorded 2026-09-22 e626bd567c81f207 · report
fixture: returned Storage · level recorded 2026-09-22 2439c728712b51ae · report
fixture: signature indices:ndarray/1/int, batch_size:int/0/int · returned generator · level recorded 2026-09-22 bab8cee03856463f · report
fixture: returned ActorCritic · level recorded 2026-09-22 bd4134c19ff6f1eb · report
fixture: returned PPO · level recorded 2026-09-22 22bcf7bc55b864b8 · report
fixture: returned RolloutBuffer · level recorded 2026-09-22 75bc51af9c0cf574 · report
fixture: returned MemoryPPO · level recorded 2026-09-22 f473685be4b59e7f · report
6647017115e92ee7 · report
a9432edcc1976925 · report
census: 8 implementations from 9 papers, 7 distinct outputs across 5 buckets, one shared input per bucket models/ppo/model.py unverified no licence file found · pointer only ·
6b56455d8ddd9bf1 · report
48d2039b794ca629 · report
942f9baf61103bea · report
fixture: signature policy:callable/0/?, arc:MinimalArc/0/?, epsilon:float/0/float · returned Tensor · level recorded 2026-09-22 62a48793f7edb3af · report
fixture: signature rewards:Tensor/2/float, values:Tensor/2/float, mask_n:Tensor/2/float, gamma:float/0/float, lam:float/0/float · returned tuple · level recorded 2026-09-22 356537802e7b2bdb · report
fixture: signature rewards:list/1/float, mask_n:list/1/float, gamma:float/0/float · returned list · level recorded 2026-09-22 76b542040b4e4fcf · report
542d8a7c56874ec9 · report
e33afa03c0df2bff · report
fixture: returned PPO · level recorded 2026-09-22 f1449fb45454e326 · report
fixture: signature simulator:SimpleSimulator/0/?, actor_model:callable/0/?, count:int/0/int, min_value:float/0/float, max_value:float/0/float, sigma:float/0/float, init_step:int/0/int, gamma:float/0/float · returned list · level recorded 2026-09-22 d068adb7cb463c20 · report
f51a9f6b2ca368d9 · report
c02c0631708465dc · report
fixture: returned Policy · level recorded 2026-09-22 1ebfd098cf241f3c · report
fixture: returned PPO · level recorded 2026-09-22 c80e9a362666d32e · report
fixture: returned Runner · level recorded 2026-09-22 5b125d5154c21cbf · report
14b4f65f714ccf75 · report
be674cc9da531aa5 · report
13b852ad71d18604 · report
fixture: signature x:Tensor/2/float · returned tuple · level recorded 2026-09-24 1a18a57c9dbc3655 · report
fixture: returned CriticNet · level recorded 2026-09-22 64930ee88e057fb9 · report
f42b9cecada07086 · report
20cf521175a91e97 · report
fixture: returned PPO · level recorded 2026-09-22 9619638a806c794f · report
5954e04c0ee7d26e · report
63380712f9af778d · report
fixture: signature logits:Tensor/3/float, labels:Tensor/2/int · returned Tensor · level recorded 2026-09-22 0db440a845c6a4fa · report
fixture: signature old_logprob:EagerTensor/2/float, new_logprob:EagerTensor/2/float, epsilon:EagerTensor/0/float, advantage:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22 00bb1a30b070c324 · report
fixture: returned PPO · level recorded 2026-09-22 3 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
8758308dc6c0727f · report
fixture: signature val:int/0/int · returned function · level recorded, date not recorded Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
64 assemblies on this paper: 64 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
64 sibling assemblies for Proximal Policy Optimization (PPO) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 64 sibling assemblies; the other 52 are listed with their counts; every brick is in this page's JSON twin.
harvested Assembly for Proximal Policy Optimization (PPO) (graph method: Proximal Policy Optimization (PPO)). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 64 siblings
- proximal_policy_optimization_loss entry · level 1 · ran · our draft was wrong ·
063d29364d7e4f81
harvested Assembly for Proximal Policy Optimization (PPO) (graph method: Proximal Policy Optimization (PPO)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 64 siblings
- PPO entry · level 1 · ran ·
1ebfd098cf241f3c
harvested Assembly for Proximal Policy Optimization (PPO) (graph method: Proximal Policy Optimization (PPO)). 12 bricks; individually on a fixture: 10 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 64 siblings
- PPO_continuous entry · level 0 · unverified ·
5dc5fc3b8ad0138c - Algorithm helper · level 0 · unverified ·
d5c516ed0fa589e3 - RolloutBuffer_PPO_lag helper · level 1 · ran ·
6f986aa2d59a44f8 - StateFunction helper · level 1 · ran ·
a78ee4761e8df9d8 - StateIndependentPolicy helper · level 1 · ran ·
fbd28096c7f0c30f - calculate_gae helper · level 1 · ran · our draft was wrong ·
b5a22b5e0dce3796 - calculate_gae_cost helper · level 1 · ran · our draft was wrong ·
77393baa1a11c24b - build_mlp helper · level 1 · ran · our draft was wrong ·
c511268a73d82fc6 - evaluate_lop_pi helper · level 1 · ran · honoured contract ·
fef4ec37a6ea52e7 - reparameterize helper · level 1 · ran · our draft was wrong ·
b1c9c127240c75d8 - atanh helper · level 1 · ran · honoured contract ·
264c9e17d7dfe7eb - calculate_log_pi helper · level 1 · ran · honoured contract ·
476e14ee8b7219ac
harvested Assembly for Proximal Policy Optimization (PPO) (graph method: Proximal Policy Optimization (PPO)). 3 bricks; individually on a fixture: 0 ran · 3 unverified. The assembly has not been run end-to-end.
one of 64 siblings
harvested Assembly for Proximal Policy Optimization (PPO) (graph method: Proximal Policy Optimization (PPO)). 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 64 siblings
- clipped_surrogate entry · level 0 · unverified ·
9c65b36eec7ec92a - states_to_prob model · level 1 · ran · our draft was wrong ·
a7700bf49f384087
harvested Assembly for Proximal Policy Optimization (PPO) (graph method: Proximal Policy Optimization (PPO)). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 64 siblings
- PPO entry · level 0 · unverified ·
5954e04c0ee7d26e
harvested Assembly for Proximal Policy Optimization (PPO) (graph method: Proximal Policy Optimization (PPO)). 4 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 64 siblings
- Agent entry · level 1 · ran ·
b1f30e180cb81a3a - ActorCritic model · level 1 · ran ·
f7a59411ac390f78 - Actor model · level 1 · ran ·
e9f1207fc08f9fa9 - Critic model · level 1 · ran ·
b4455ab1f545ae9c
harvested Assembly for Proximal Policy Optimization (PPO) (graph method: Proximal Policy Optimization (PPO)). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 64 siblings
- PongAgent entry · level 0 · unverified ·
40f05c72bfe4c048 - Policy model · level 1 · ran ·
c02c0631708465dc
harvested Assembly for Proximal Policy Optimization (PPO) (graph method: Proximal Policy Optimization (PPO)). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 64 siblings
- Agent entry · level 0 · unverified ·
f473685be4b59e7f - MemoryPPO data_transform · level 1 · ran ·
75bc51af9c0cf574
harvested Assembly for Proximal Policy Optimization (PPO) (graph method: Proximal Policy Optimization (PPO)). 4 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 64 siblings
- PPO entry · level 1 · ran ·
b48c75c1f791937c - PolicyUpdate update_rule · level 1 · ran ·
2eb0c930a45a7472 - ppo_loss loss · level 0 · unverified ·
2c9a98eedcdea762 - ModelUpdate helper · level 1 · ran ·
7f143a6ee276436b
harvested Assembly for Proximal Policy Optimization (PPO) (graph method: Proximal Policy Optimization (PPO)). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 64 siblings
- PPOalgorithm entry · level 0 · unverified ·
bce2a8566fa36fda
harvested Assembly for Proximal Policy Optimization (PPO) (graph method: Proximal Policy Optimization (PPO)). 4 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.
one of 64 siblings
- PPOAgent entry · level 0 · unverified ·
01b7328f523d7756 - Actor model · level 0 · unverified ·
bf0c1da602f8a16d - Critic model · level 0 · unverified ·
708e869097ea91ff - gaussian_likelihood helper · level 1 · ran · honoured contract ·
b46c632bedd3d8af
- learn · 3d1f2cc06035ea0a · 7 bricks; individually on a fixture: 4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
- Model · 4001252face0416d · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
- ppo_loss · 44d8b39d2fb476c9 · 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
- PPO · 452ce971591430ce · 3 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
- Agent · 484ddcf0d4356b8c · 4 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
- surrogate_loss · 4ce5af77fa6f4833 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[17] in the JSON twin
- PPO · 4dc0f5bbcea8f6cb · 12 bricks; individually on a fixture: 8 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
- PPO · 4f2cdd5736c5ac05 · 4 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[19] in the JSON twin
- PPO · 545631e1506660a9 · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[20] in the JSON twin
- train · 56dc80195a79d4ab · 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[21] in the JSON twin
- PPO · 5c85085383d91168 · 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[22] in the JSON twin
- PPOAlgo · 5e8e5bc0133684ff · 7 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[23] in the JSON twin
- PPO · 5f670b9e0bff80cc · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[24] in the JSON twin
- Agent · 65fea45a5fbcf003 · 3 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[25] in the JSON twin
- PPO_CLIP · 67465e0454ae1502 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[26] in the JSON twin
- ppo_update · 69dcc57ca900f4a9 · 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[27] in the JSON twin
- PPO · 6c6488eaf07c5cd2 · 11 bricks; individually on a fixture: 9 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[28] in the JSON twin
- PPO · 7b781a51dbdb10eb · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[29] in the JSON twin
- PPO · 820466280dda9c76 · 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[30] in the JSON twin
- PPOAlgo · 83b8ef33e9af0b97 · 6 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[31] in the JSON twin
- proximal_policy_optimization_loss · 8693af6c0b7a4743 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[32] in the JSON twin
- clipped_surrogate · 86bd407862da2411 · 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[33] in the JSON twin
- PPO · 8b3d19783f5c610b · 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[34] in the JSON twin
- Policy · 8c140ab8c777ee63 · 3 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[35] in the JSON twin
- PPO · 8d6590892a5b6996 · 9 bricks; individually on a fixture: 5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified · The assembly has not been run end-to-end · assemblies[36] in the JSON twin
- PPO · 8d6fee5945f49846 · 3 bricks; individually on a fixture: 0 ran · 3 unverified · The assembly has not been run end-to-end · assemblies[37] in the JSON twin
- PPOAgent · 90c9b8afd1f6f185 · 4 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[38] in the JSON twin
- ppo_clip_loss · 93e3c144f2fcebec · 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[39] in the JSON twin
- ppo_update · 95e7acfe51a56ff3 · 3 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[40] in the JSON twin
- PPOAlgorithm · 963202faa4c5bea5 · 3 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[41] in the JSON twin
- PPOAgent · 98f7bb203dda6920 · 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[42] in the JSON twin
- PPO · 9d8ce58b69147416 · 5 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[43] in the JSON twin
- build_train · 9dc95a3cfa84d169 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[44] in the JSON twin
- update · aa2577adcf955e3d · 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[45] in the JSON twin
- update · ae803636ac0600a8 · 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[46] in the JSON twin
- PPO · afcac13d8faac401 · 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[47] in the JSON twin
- PPO · bb25dd31a314de78 · 12 bricks; individually on a fixture: 10 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[48] in the JSON twin
- PPONetwork · be99ff2dc064352d · 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[49] in the JSON twin
- proximal_policy_optimization_loss_continuous · bf7a5807bc6decbb · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[50] in the JSON twin
- PPO · c31a1b29be6dccc4 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[51] in the JSON twin
- Agent · c62f861f771b9563 · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[52] in the JSON twin
- PPO · c8b3266a6c71954e · 3 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[53] in the JSON twin
- ppo_step · c9442e5f1a3f07c0 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[54] in the JSON twin
- PPO · ca966194ac6bde41 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[55] in the JSON twin
- update · ce5631d908c867ec · 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[56] in the JSON twin
- PPO · cf9f22ce8d9df0b1 · 3 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[57] in the JSON twin
- Policy · d10b94a897b575c0 · 3 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[58] in the JSON twin
- PPO · d2c6885423d4aecf · 3 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[59] in the JSON twin
- MyPPO · e1139e085618d3a6 · 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[60] in the JSON twin
- PPOAgent · e4bbf4ae4dbdaceb · 4 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[61] in the JSON twin
- PPO · ea8574b6125d04b0 · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[62] in the JSON twin
- PPO_lunarlander · f2c646ce0523c173 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[63] in the JSON twin
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1707.06347") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Continuous Control | Lunar Lander (OpenAI Gym) | PPO | Score | 175.14±44.94 | #4 of 5 | Archive leaderboard | report |
| Neural Architecture Search | NATS-Bench Topology, CIFAR-10 | PPO (Schulman et al., 2017) | Test Accuracy | 94.02 | #3 of 11 | Archive leaderboard | report |
| Neural Architecture Search | NATS-Bench Topology, CIFAR-100 | PPO (Schulman et al., 2017) | Test Accuracy | 71.68 | #2 of 11 | Archive leaderboard | report |
| Neural Architecture Search | NATS-Bench Topology, ImageNet16-120 | PPO (Schulman et al., 2017) | Test Accuracy | 44.95 | #3 of 11 | Archive leaderboard | report |
| OpenAI Gym | Ant-v4 | PPO | Average Return | 608.97 | #5 of 5 | Archive leaderboard | report |
| OpenAI Gym | HalfCheetah-v4 | PPO | Average Return | 6006.11 | #5 of 5 | Archive leaderboard | report |
| OpenAI Gym | Hopper-v4 | PPO | Average Return | 790.77 | #5 of 5 | Archive leaderboard | report |
| OpenAI Gym | Humanoid-v4 | PPO | Average Return | 925.89 | #3 of 5 | Archive leaderboard | report |
| OpenAI Gym | Walker2d-v4 | PPO | Average Return | 2739.81 | #4 of 5 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Introduced by this paper: PPO
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections