Papers › Decision Transformer: Reinforcement Learning via Sequence Modeling

Decision Transformer: Reinforcement Learning via Sequence Modeling

2 Jun 2021NeurIPS 2021 12arXiv:2106.01345archive 2025-07-28

Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, Igor Mordatch

We introduce a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem. This allows us to draw upon the simplicity and scalability of the Transformer architecture, and associated advances in language modeling such as GPT-x and BERT. In particular, we present Decision Transformer, an architecture that casts the problem of RL as conditional sequence modeling. Unlike prior approaches to RL that fit value functions or compute policy gradients, Decision Transformer simply outputs the optimal actions by leveraging a causally masked Transformer. By conditioning an autoregressive model on the desired return (reward), past states, and actions, our Decision Transformer model can generate future actions that achieve the desired return. Despite its simplicity, Decision Transformer matches or exceeds the performance of state-of-the-art model-free offline RL baselines on Atari, OpenAI Gym, and Key-to-Door tasks.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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):

Code

No sample from the archive's official repository (kzl/decision-transformer) is linked to this paper; the 26 samples below come from 11 community repositories. Syntology harvested code from kzl/decision-transformer for another paper.

kzl/decision-transformer: Syntology's graph links these samples to Online Decision Transformer (arXiv:2202.05607; that paper's own run record: 2 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; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.

Syntology 26 code samples harvested from 11 repositories linked to this paper: 17 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 4 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): 26 samples from 11 repositories, 17 ran (12 with no instrument failure; 5 where Syntology's instrument failed). 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 7 of its repositories that Syntology harvested for other papers:

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 17 samples that ran have no recorded date.

20 repositories listed; official and paper-mentioned ones first.

kzl/decision-transformer officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Online Decision Transformer (arXiv:2202.05607; that paper's own run record: 2 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; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Amadeus979/decision-transformer mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
Delavari-Alireza/Decision_Transformer_Sequence-Modeling_Deep_Reinforcement_Learning mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
LAS1520/Gato-A-Generalist-Agent mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
RamiSketcher/decision-transformer-ammi mentioned on GitHubpytorchSyntology: not harvested report
cannylab/casual_overhypotheses mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Towards Understanding How Machines Can Learn Causal Overhypotheses (arXiv:2206.08353; that paper's own run record: 3 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; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
corl-team/CORL mentioned on GitHubjaxSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
facebookresearch/salina mentioned on GitHubjaxSyntology: 4 samples, 3 ran (2 instrument-failed) · 1 unverified report
ml-jku/l2m mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning to Modulate pre-trained Models in RL (arXiv:2306.14884; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
nikhilbarhate99/min-decision-transformer mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
opendilab/DI-engine mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
takuseno/d3rlpy mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Revisiting the Minimalist Approach to Offline Reinforcement Learning (arXiv:2305.09836; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
typoverflow/OfflineRL-Lib mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Offline Reinforcement Learning with Implicit Q-Learning (arXiv:2110.06169; that paper's own run record: 45 ran (of which 23 constructed an object rather than computing a result; 36 with no instrument failure: 0 honoured, 0 violated, 36 with no contract checked; 9 where Syntology's instrument failed) · 13 unverified) and Extreme Q-Learning: MaxEnt RL without Entropy (arXiv:2301.02328; that paper's own run record: 8 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
yun-kwak/decision-transformer-jax mentioned on GitHubjaxSyntology: 4 samples, 0 ran · 4 unverified report
zzmtsvv/rl_task mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
2024-MindSpore-1/Code2 mindsporeSyntology: not harvested report
HzcIrving/DecisionTransformer_StepbyStep pytorchMITSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
MindCode-4/code-3 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models... (arXiv:2406.18321; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
pwc-1/Paper-8 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models... (arXiv:2406.18321; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
pytorch/rl jaxSyntology: 1 sample, 0 ran · 1 unverified report

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

26 samples harvested: 17 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · our draft was wrong
1ran; the contract check could not run
12ran
9unverified

Licence: 8 of the 26 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 11 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. “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 2 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.

Amadeus979/decision-transformer community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
evaluate_episode in 8 papers gym/decision_transformer/evaluation/evaluate_episodes.py ran · our draft was wrong MIT (permissive) · 1ed718456cb9f7a0 · report fixture: signature env:MockEnv/0/?, state_dim:int/0/int, act_dim:int/0/int, model:callable/0/?, max_ep_len:int/0/int, device:str/0/str, target_return:float/0/float, mode:str/0/str, state_mean:ndarray/1/float, state_std:ndarray/1/float · returned tuple · level recorded 2026-09-24
evaluate_episode_rtg in 8 papers gym/decision_transformer/evaluation/evaluate_episodes.py ran · our draft was wrong MIT (permissive) · 9c904f0602da78d7 · report fixture: signature env:MockEnv/0/?, state_dim:int/0/int, act_dim:int/0/int, model:callable/0/?, max_ep_len:int/0/int, scale:float/0/float, state_mean:ndarray/1/float, state_std:ndarray/1/float, device:str/0/str, target_return:float/0/float, mode:str/0/str · returned tuple · level recorded, date not recorded
load_tf_weights_in_gpt2 in 68 papers gym/decision_transformer/models/trajectory_gpt2.py unverified MIT (permissive) here; the stored copy is pointer only · 00a33466c69c5705 · report
Delavari-Alireza/Decision_Transformer_Sequence-Modeling_Deep_Reinforcement_Learning community (archive-listed) 1 sample, 0 ran · 1 unverified
DecisionTransformer HalfCheetah/model.py unverified MIT (permissive) · e8829585a4a05826 · report
LAS1520/Gato-A-Generalist-Agent community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
Gato_models/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · e3c3fcca273a8e47 · report fixture: returned Block · level recorded 2026-09-22
DecisionTransformer Gato_models/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 6daf6f8401bed739 · report fixture: returned DecisionTransformer · level recorded 2026-09-22
MaskedCausalAttention in 5 papers Gato_models/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 621a87d0ebc957c4 · report fixture: returned MaskedCausalAttention · level recorded 2026-09-22
corl-team/CORL community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
DecisionTransformer algorithms/offline/dt.py ran Apache-2.0 (permissive) · a437b4b107300a41 · report fixture: returned DecisionTransformer · level recorded 2026-09-22
TransformerBlock in 73 papers algorithms/offline/dt.py ran Apache-2.0 (permissive) · d879368facd3289e · report fixture: returned TransformerBlock · level recorded 2026-09-22
facebookresearch/salina community (archive-listed) 4 samples, 3 ran (2 instrument-failed) · 1 unverified
Agent in 42 papers salina_examples/offline_rl/decision_transformer/agents.py ran · metamorphic tier: deterministic MIT (permissive) · 89113bc52fb73297 · report fixture: returned Agent · level recorded 2026-09-22
instantiate_class in 7 papers salina_examples/offline_rl/decision_transformer/agents.py ran · our draft was wrong MIT (permissive) · 77a7fd5bc546c3a1 · report fixture: signature arguments:dict/0/? · returned Linear · level recorded 2026-09-22
mlp in 108 papers salina_examples/offline_rl/decision_transformer/agents.py ran · our draft was wrong MIT (permissive) · 4e4aebc21d42fb20 · report fixture: signature sizes:list/1/int, activation:callable/0/?, output_activation:callable/0/? · returned Sequential · level recorded 2026-09-22
ActionMLPAgentFromTransformer salina_examples/offline_rl/decision_transformer/agents.py unverified MIT (permissive) · 81de786f2fb6de0b · report
nikhilbarhate99/min-decision-transformer community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DecisionTransformer decision_transformer/model.py ran MIT (permissive) · 815b0c86f32c99cc · report fixture: returned DecisionTransformer · level recorded 2026-09-22
opendilab/DI-engine community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
ding/model/template/decision_transformer.py ran Apache-2.0 (permissive) · 25243005f892c666 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
MaskedCausalAttention in 5 papers ding/model/template/decision_transformer.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 23842a66d5113ef0 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
DecisionTransformer ding/model/template/decision_transformer.py unverified Apache-2.0 (permissive) · d6dc19545c453079 · report
yun-kwak/decision-transformer-jax community (archive-listed) 4 samples, 0 ran · 4 unverified
CausalSelfAttention in 28 papers dt_jax/gpt.py unverified MIT (permissive) · 143914639aea2cb9 · report
Dropout in 8 papers dt_jax/gpt.py unverified MIT (permissive) · 2a9e66156b160093 · report
GPT in 24 papers dt_jax/gpt.py unverified MIT (permissive) · b1501ba16b463b22 · report
TransformerBlock in 73 papers dt_jax/gpt.py unverified MIT (permissive) · 9b48d1222dabdd2c · report
zzmtsvv/rl_task community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
DecisionTransformer decision_transformer/model.py ran no licence file found · pointer only · dfabbac8bf8010df · report fixture: returned DecisionTransformer · level recorded 2026-09-22
TransformerBlock in 73 papers decision_transformer/model.py ran no licence file found · pointer only · 12cc4b7038955563 · report fixture: returned TransformerBlock · level recorded 2026-09-22
dt_config decision_transformer/model.py ran no licence file found · pointer only · 30bf51af033aeb98 · report fixture: returned dt_config · level recorded 2026-09-22
HzcIrving/DecisionTransformer_StepbyStep community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
discount_cumsum in 35 papers
census: 6 implementations from 13 papers, 3 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 1, kind float, dtype float64
utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · 0161b27cbe3cc58d · report fixture: signature x:ndarray/1/float, gamma:float/0/float · returned ndarray · level recorded, date not recorded
pytorch/rl community (archive-listed) 1 sample, 0 ran · 1 unverified
DecisionTransformer torchrl/modules/models/decision_transformer.py unverified MIT (permissive) · 5cbb6e8c7b3ba6c7 · report

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.

9 assemblies on this paper: 9 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

9 sibling assemblies for Decision Transformer (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Decision Transformer (graph method: Decision Transformer). 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.

one of 9 siblings

  1. DecisionTransformer entry · level 1 · ran · 6daf6f8401bed739
  2. Block model · level 1 · ran · e3c3fcca273a8e47
  3. MaskedCausalAttention model · level 1 · ran · 621a87d0ebc957c4

harvested Assembly for Decision Transformer (graph method: Decision Transformer). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. DecisionTransformer entry · level 0 · unverified · e8829585a4a05826

harvested Assembly for Decision Transformer (graph method: Decision Transformer). 4 bricks; individually on a fixture: 3 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; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. ActionMLPAgentFromTransformer entry · level 0 · unverified · 81de786f2fb6de0b
  2. Agent helper · level 1 · ran · 89113bc52fb73297
  3. instantiate_class helper · level 1 · ran · our draft was wrong · 77a7fd5bc546c3a1
  4. mlp model · level 1 · ran · our draft was wrong · 4e4aebc21d42fb20

harvested Assembly for Decision Transformer (graph method: Decision Transformer). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. DecisionTransformer entry · level 0 · unverified · 5cbb6e8c7b3ba6c7

harvested Assembly for Decision Transformer (graph method: Decision Transformer). 2 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) · 0 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.

one of 9 siblings

  1. DecisionTransformer entry · level 1 · ran · a437b4b107300a41
  2. TransformerBlock model · level 1 · ran · d879368facd3289e

harvested Assembly for Decision Transformer (graph method: Decision Transformer). 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.

one of 9 siblings

  1. DecisionTransformer entry · level 1 · ran · dfabbac8bf8010df
  2. TransformerBlock model · level 1 · ran · 12cc4b7038955563
  3. dt_config helper · level 1 · ran · 30bf51af033aeb98

harvested Assembly for Decision Transformer (graph method: Decision Transformer). 4 bricks; individually on a fixture: 0 ran · 4 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. GPT entry · level 0 · unverified · b1501ba16b463b22
  2. Dropout helper · level 0 · unverified · 2a9e66156b160093
  3. TransformerBlock model · level 0 · unverified · 9b48d1222dabdd2c
  4. CausalSelfAttention model · level 0 · unverified · 143914639aea2cb9

harvested Assembly for Decision Transformer (graph method: Decision Transformer). 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.

one of 9 siblings

  1. DecisionTransformer entry · level 1 · ran · 815b0c86f32c99cc
  2. Block model · level 1 · ran · 0340d1b0f37688a5
  3. MaskedCausalAttention model · level 1 · ran · 7a7dab71d814fea4

harvested Assembly for Decision Transformer (graph method: Decision Transformer). 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.

one of 9 siblings

  1. DecisionTransformer entry · level 0 · unverified · d6dc19545c453079
  2. Block model · level 1 · ran · 25243005f892c666
  3. MaskedCausalAttention model · level 1 · ran · 23842a66d5113ef0

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="2106.01345") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Atari GamesD4RLLanguage ModelingLanguage ModellingOffline RLOpenAI GymReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Atari Games Atari 2600 Breakout DT Score 267.5 #44 of 58 Archive leaderboard report
Atari Games Atari 2600 Pong DT Score 17.1 #43 of 52 Archive leaderboard report
Atari Games Atari 2600 Q*Bert DT Score 25.1 #56 of 57 Archive leaderboard report
Atari Games Atari 2600 Seaquest DT Score 2.4 #56 of 57 Archive leaderboard report
D4RL D4RL Decision Transformer (DT) Average Reward 72.2 #5 of 9 Archive leaderboard report
Offline RL D4RL Decision Transformer (DT) Average Reward 73.5 #3 of 3 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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