Papers › Addressing Function Approximation Error in Actor-Critic Methods

Addressing Function Approximation Error in Actor-Critic Methods

26 Feb 2018ICML 2018 7arXiv:1802.09477archive 2025-07-28

Scott Fujimoto, Herke van Hoof, David Meger

In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies. We show that this problem persists in an actor-critic setting and propose novel mechanisms to minimize its effects on both the actor and the critic. Our algorithm builds on Double Q-learning, by taking the minimum value between a pair of critics to limit overestimation. We draw the connection between target networks and overestimation bias, and suggest delaying policy updates to reduce per-update error and further improve performance. We evaluate our method on the suite of OpenAI gym tasks, outperforming the state of the art in every environment tested.

PaperPDFConference PDFCodeCode Syntology ran

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 (sfujim/TD3) is linked to this paper; the 36 samples below come from 8 community repositories. Syntology harvested code from sfujim/TD3 for 2 other papers.

sfujim/TD3: Syntology's graph links these samples to Estimating Q(s,s') with Deep Deterministic Dynamics Gradients (arXiv:2002.09505; that paper's own run record: 6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 6 samples that ran constructed an object rather than computing a result) and Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control (arXiv:2405.16158; that paper's own run record: 11 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method.

Syntology 36 code samples harvested from 8 repositories linked to this paper: 26 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 2 violated, 17 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 36 samples from 8 repositories, 26 ran (20 with no instrument failure; 6 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 29 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 26 samples that ran has no recorded date.

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

sfujim/TD3 officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Estimating Q(s,s') with Deep Deterministic Dynamics Gradients (arXiv:2002.09505; that paper's own run record: 6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 6 samples that ran constructed an object rather than computing a result) and Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control (arXiv:2405.16158; that paper's own run record: 11 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
CharlotteMorrison/Baxter-Research mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Prioritized Experience Replay (arXiv:1511.05952; that paper's own run record: 80 ran (of which 62 constructed an object rather than computing a result; 72 with no instrument failure: 4 honoured, 0 violated, 68 with no contract checked; 8 where Syntology's instrument failed) · 31 unverified); nothing checks that they implement this paper's method. report
CharlotteMorrison/Baxter-VREP mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Prioritized Experience Replay (arXiv:1511.05952; that paper's own run record: 80 ran (of which 62 constructed an object rather than computing a result; 72 with no instrument failure: 4 honoured, 0 violated, 68 with no contract checked; 8 where Syntology's instrument failed) · 31 unverified); nothing checks that they implement this paper's method. report
CharlotteMorrison/Baxter-VREP-Version-2 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Prioritized Experience Replay (arXiv:1511.05952; that paper's own run record: 80 ran (of which 62 constructed an object rather than computing a result; 72 with no instrument failure: 4 honoured, 0 violated, 68 with no contract checked; 8 where Syntology's instrument failed) · 31 unverified); nothing checks that they implement this paper's method. report
DanielTakeshi/DCUR mentioned on GitHubpytorchMITSyntology: 9 samples, 6 ran (0 instrument-failed) · 3 unverified report
GauravPatel89/Car-Navigation-Simulation-using-TD3 mentioned on GitHubpytorchSyntology: not harvested report
GhadaSokar/Dynamic-Sparse-Training-for-Deep-Reinforcement-Learning mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Dynamic Sparse Training for Deep Reinforcement Learning (arXiv:2106.04217; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
JohannesAck/MATD3implementation mentioned on GitHubtfSyntology: not harvested report
MrSyee/pg-is-all-you-need mentioned on GitHubMITSyntology: not harvested report
Rafael1s/Deep-Reinforcement-Learning-Udacity mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Proximal Policy Optimization Algorithms (arXiv:1707.06347; that paper's own run record: 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) and Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a... (arXiv:1801.01290; that paper's own run record: 91 ran (of which 61 constructed an object rather than computing a result; 73 with no instrument failure: 3 honoured, 1 violated, 69 with no contract checked; 18 where Syntology's instrument failed) · 57 unverified); nothing checks that they implement this paper's method. report
SaminYeasar/off_policy_ac mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Continuous control with deep reinforcement learning (arXiv:1509.02971; that paper's own run record: 163 ran (of which 126 constructed an object rather than computing a result; 152 with no instrument failure: 3 honoured, 0 violated, 149 with no contract checked; 11 where Syntology's instrument failed) · 143 unverified) and Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a... (arXiv:1801.01290; that paper's own run record: 91 ran (of which 61 constructed an object rather than computing a result; 73 with no instrument failure: 3 honoured, 1 violated, 69 with no contract checked; 18 where Syntology's instrument failed) · 57 unverified); nothing checks that they implement this paper's method. report
SeungeonBaek/continuous-agents-test mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Implicit Distributional Reinforcement Learning (arXiv:2007.06159; that paper's own run record: 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) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method. report
VasaKiDD/TD3-deep-rl-research mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Zartris/TD3_continuous_control mentioned on GitHubpytorchSyntology: not harvested report
adaptive-intelligent-robotics/pga-map-elites mentioned on GitHubpytorchSyntology: not harvested report
andreidi/AC_DDPG_walker mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Continuous control with deep reinforcement learning (arXiv:1509.02971; that paper's own run record: 163 ran (of which 126 constructed an object rather than computing a result; 152 with no instrument failure: 3 honoured, 0 violated, 149 with no contract checked; 11 where Syntology's instrument failed) · 143 unverified); nothing checks that they implement this paper's method. report
andrejorsula/drl_grasping mentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Mastering Atari with Discrete World Models (arXiv:2010.02193; that paper's own run record: 11 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
araffin/sbx mentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning (arXiv:2410.09754; that paper's own run record: 6 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
arrival-ltd/catalyst-rl-tutorial mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Sample Efficient Ensemble Learning with Catalyst.RL (arXiv:2003.14210; that paper's own run record: 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) · 1 unverified); nothing checks that they implement this paper's method. report
ashaaher/Reinforcement-Learning-Project mentioned on GitHubpytorchSyntology: not harvested report
b06b01073/Twin-Delayed-DDPG mentioned on GitHubpytorchSyntology: not harvested report
baturaysaglam/ac-off-poc mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Continuous control with deep reinforcement learning (arXiv:1509.02971; that paper's own run record: 163 ran (of which 126 constructed an object rather than computing a result; 152 with no instrument failure: 3 honoured, 0 violated, 149 with no contract checked; 11 where Syntology's instrument failed) · 143 unverified); nothing checks that they implement this paper's method. report
baturaysaglam/dase mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
baturaysaglam/la3p mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a... (arXiv:1801.01290; that paper's own run record: 91 ran (of which 61 constructed an object rather than computing a result; 73 with no instrument failure: 3 honoured, 1 violated, 69 with no contract checked; 18 where Syntology's instrument failed) · 57 unverified); nothing checks that they implement this paper's method. report
ccolas/rl_stats mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms (arXiv:1904.06979; that paper's own run record: 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); nothing checks that they implement this paper's method. report
chainer/chainerrl mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ChainerRL: A Deep Reinforcement Learning Library (arXiv:1912.03905; that paper's own run record: 1 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; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
claudeHifly/BipedalWalker-v3 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Continuous control with deep reinforcement learning (arXiv:1509.02971; that paper's own run record: 163 ran (of which 126 constructed an object rather than computing a result; 152 with no instrument failure: 3 honoured, 0 violated, 149 with no contract checked; 11 where Syntology's instrument failed) · 143 unverified); nothing checks that they implement this paper's method. report
core-robotics-lab/icct mentioned on GitHubpytorchMITSyntology: not harvested report
coreylowman/rl_simply mentioned on GitHubpytorchSyntology: not harvested report
crazyleg/TD3-reacher mentioned on GitHubpytorchMITSyntology: not harvested report
facebookresearch/ReAgent mentioned on GitHubpytorchSyntology: not harvested report
fdcl-gwu/gym-rotor mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics (arXiv:1910.01465; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
fiorenza2/OffCon3 mentioned on GitHubpytorchSyntology: not harvested report
flowersteam/rl_stats mentioned on GitHubSyntology: not harvested report
georgesung/TD3 mentioned on GitHubpytorchSyntology: not harvested report
gwthomas/gtml mentioned on GitHubtfSyntology: not harvested report
intelligent-environments-lab/CityLearn mentioned on GitHubtfSyntology: not harvested report
jaem-seo/AI_tokamak_control mentioned on GitHubMITSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
jyqhahah/rl_maddpg_matd3 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments (arXiv:1706.02275; that paper's own run record: 75 ran (of which 54 constructed an object rather than computing a result; 68 with no instrument failure: 2 honoured, 0 violated, 66 with no contract checked; 7 where Syntology's instrument failed) · 68 unverified); nothing checks that they implement this paper's method. report
kairproject/kair_algorithms_draft mentioned on GitHubpytorchSyntology: not harvested report
markub3327/rl-agent mentioned on GitHubtfMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
markub3327/rl-baselines mentioned on GitHubtfMITSyntology: not harvested report
markub3327/rl-toolkit mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Smooth Exploration for Robotic Reinforcement Learning (arXiv:2005.05719; that paper's own run record: 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); nothing checks that they implement this paper's method. report
marload/DeepRL-TensorFlow2 mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Playing Atari with Deep Reinforcement Learning (arXiv:1312.5602; that paper's own run record: 64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 unverified), Continuous control with deep reinforcement learning (arXiv:1509.02971; that paper's own run record: 163 ran (of which 126 constructed an object rather than computing a result; 152 with no instrument failure: 3 honoured, 0 violated, 149 with no contract checked; 11 where Syntology's instrument failed) · 143 unverified), Deep Reinforcement Learning with Double Q-learning (arXiv:1509.06461; that paper's own run record: 56 ran (of which 38 constructed an object rather than computing a result; 55 with no instrument failure: 0 honoured, 0 violated, 55 with no contract checked; 1 where Syntology's instrument failed) · 50 unverified) and 2 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore mentioned on GitHubmindsporeSyntology: not harvested report
nikhilbarhate99/TD3-PyTorch-BipedalWalker-v2 mentioned on GitHubpytorchMITSyntology: not harvested report
ollenilsson19/MAP-Elites-GAPG mentioned on GitHubpytorchMITSyntology: 5 samples, 3 ran (1 instrument-failed) · 2 unverified report
ollenilsson19/PGA-MAP-Elites mentioned on GitHubpytorchMITSyntology: not harvested report
patrickhart/jaxdl mentioned on GitHubjaxMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Soft Actor-Critic Algorithms and Applications (arXiv:1812.05905; that paper's own run record: 38 ran (of which 0 constructed an object rather than computing a result; 35 with no instrument failure: 4 honoured, 1 violated, 30 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
pkasala/ContinuesControl mentioned on GitHubpytorchSyntology: not harvested report
quantumiracle/Popular-RL-Algorithms mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a... (arXiv:1801.01290; that paper's own run record: 91 ran (of which 61 constructed an object rather than computing a result; 73 with no instrument failure: 3 honoured, 1 violated, 69 with no contract checked; 18 where Syntology's instrument failed) · 57 unverified); nothing checks that they implement this paper's method. report
reiniscimurs/TD3_Separate_Action mentioned on GitHubpytorchSyntology: not harvested report
robintyh1/icml2021-pengqlambda mentioned on GitHubtfMITSyntology: 11 samples, 7 ran (5 instrument-failed) · 4 unverified report
rshnn/battleship mentioned on GitHubSyntology: not harvested report
soumik12345/Twin-Delayed-DDPG mentioned on GitHubpytorchSyntology: not harvested report
tensorlayer/RLzoo mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Trust Region Policy Optimization (arXiv:1502.05477; that paper's own run record: 7 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified), Continuous control with deep reinforcement learning (arXiv:1509.02971; that paper's own run record: 163 ran (of which 126 constructed an object rather than computing a result; 152 with no instrument failure: 3 honoured, 0 violated, 149 with no contract checked; 11 where Syntology's instrument failed) · 143 unverified), Deep Reinforcement Learning with Double Q-learning (arXiv:1509.06461; that paper's own run record: 56 ran (of which 38 constructed an object rather than computing a result; 55 with no instrument failure: 0 honoured, 0 violated, 55 with no contract checked; 1 where Syntology's instrument failed) · 50 unverified) and 3 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
tomaszsmaruj25/Twin-Delayed-DDPG-Implementation mentioned on GitHubSyntology: not harvested report
yifan12wu/td3-jax mentioned on GitHubjaxMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
yydsok/oparl mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
BIT-aerial-robotics/AquaML tfSyntology: not harvested report
DLR-RM/stable-baselines3 pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal Transport (arXiv:2603.01771; that paper's own run record: 6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
hill-a/stable-baselines tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Reinforcement Learning with Double Q-learning (arXiv:1509.06461; that paper's own run record: 56 ran (of which 38 constructed an object rather than computing a result; 55 with no instrument failure: 0 honoured, 0 violated, 55 with no contract checked; 1 where Syntology's instrument failed) · 50 unverified) and Prioritized Experience Replay (arXiv:1511.05952; that paper's own run record: 80 ran (of which 62 constructed an object rather than computing a result; 72 with no instrument failure: 4 honoured, 0 violated, 68 with no contract checked; 8 where Syntology's instrument failed) · 31 unverified); nothing checks that they implement this paper's method. report
jakegrigsby/deep_control pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Towards Automatic Actor-Critic Solutions to Continuous Control (arXiv:2106.08918; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. report
opendilab/DI-engine pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hindsight Experience Replay (arXiv:1707.01495; that paper's own run record: 16 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified), Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context (arXiv:1901.02860; that paper's own run record: 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified), Decision Transformer: Reinforcement Learning via Sequence Modeling (arXiv:2106.01345; that paper's own run record: 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) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
pytorch/rl jaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Decision Transformer: Reinforcement Learning via Sequence Modeling (arXiv:2106.01345; that paper's own run record: 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); nothing checks that they implement this paper's method. report
seungju-k1m/sac-td3-td7 pytorchSyntology: not harvested report
toni-sm/skrl jaxMITSyntology: not harvested 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

36 samples harvested: 26 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 2 violated, 17 with no contract checked; 6 where Syntology's instrument failed) · 10 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.

1ran · honoured contract
2ran · violated contract
6ran · our draft was wrong
17ran
10unverified

Licence: 21 of the 36 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 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 8 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”. “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.

DanielTakeshi/DCUR community (archive-listed) 9 samples, 6 ran (0 instrument-failed) · 3 unverified
density_scatter spinup/teaching/inspect_policy.py ran MIT recorded; this copy not marked cleared · pointer only · e0f9ede3192984c6 · report fixture: signature x:ndarray/1/float, y:ndarray/1/float, ax:Axes/0/?, fig:Figure/0/?, sort:bool/0/bool, bins:int/0/int · returned Axes · level recorded 2026-09-26
get_revised_reward spinup/teaching/offline_utils.py ran MIT recorded; this copy not marked cleared · pointer only · bd6be7742940fb51 · report fixture: signature model:callable/0/?, n_alpha:float/0/float, r_baseline:int/0/int, o:Tensor/2/float, a:Tensor/2/float, r:Tensor/1/float, o2:Tensor/2/float, d:Tensor/1/int, time:bool/0/bool, sparse:bool/0/bool · returned tuple · level recorded 2026-09-26
sample_combo_batch spinup/teaching/online_rl.py ran MIT recorded; this copy not marked cleared · pointer only · 7a6fd6ea6db8460a · report fixture: signature teacher_buf:TeacherBuffer/0/?, student_buf:StudentBuffer/0/?, batch_size:int/0/int · returned dict · level recorded 2026-09-26
sample_std spinup/teaching/load_policy.py ran MIT recorded; this copy not marked cleared · pointer only · 1b7cc1754bd06854 · report fixture: signature noise_distr:str/0/str · returned float · level recorded 2026-09-26
should_we_end_early spinup/teaching/offline_utils.py ran MIT recorded; this copy not marked cleared · pointer only · fb3b17a4bd91d20a · report fixture: returned bool · level recorded 2026-09-26
smooth in 61 papers
census: 6 implementations from 8 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
spinup/teaching/inspect_actions.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · c9672c271269cb9d · report fixture: signature values:list/1/float, weight:float/0/float · returned list · level recorded 2026-09-26
load_policy_and_env spinup/teaching/load_policy.py unverified MIT recorded; this copy not marked cleared · pointer only · a921320c1a9ef680 · report
load_policy_model spinup/teaching/inspect_actions.py unverified MIT recorded; this copy not marked cleared · pointer only · de91c09e463e0669 · report
load_pytorch_policy spinup/teaching/load_policy.py unverified MIT recorded; this copy not marked cleared · pointer only · e50af51bd256e662 · report
VasaKiDD/TD3-deep-rl-research community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
evaluate_policy in 12 papers train/main_faimemory.py ran · honoured contract Apache-2.0 (permissive) · b0a2d4b21b2d48e6 · report fixture: returned float · level recorded, date not recorded
jaem-seo/AI_tokamak_control community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
actv common/model_structure.py ran fingerprinted MIT (permissive) · b798db60af40d446 · report fixture: signature x:ndarray/2/float, method:str/0/str · returned ndarray · level recorded 2026-09-26
f2i ai_control_v0.py ran MIT (permissive) · ff2f8ee596f45c07 · report fixture: returned int · level recorded 2026-09-26
i2f ai_control_v0.py ran fingerprinted MIT (permissive) · 5fa1289490ba5c13 · report fixture: signature i:int/0/int, decimals:float/0/float · returned float · level recorded 2026-09-26
r2_k old/model_structure.py ran fingerprinted MIT (permissive) · f7d8b73059cc19fc · report fixture: signature y_true:Tensor/2/float, y_pred:Tensor/2/float · returned float · level recorded 2026-09-26
load_custom_model common/model_structure.py unverified MIT (permissive) · 2d2a11f97ea11eec · report
markub3327/rl-agent community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
cosine_schedule in 14 papers rl_toolkit/networks/callbacks/lr.py ran MIT (permissive) · 38aa9c2f06df49b7 · report fixture: signature base_lr:float/0/float, total_steps:int/0/int, warmup_steps:int/0/int · returned function · level recorded 2026-09-24
ollenilsson19/MAP-Elites-GAPG community (archive-listed) 5 samples, 3 ran (1 instrument-failed) · 2 unverified
generate_grid_configs configure_experiment/generate_configs.py ran MIT (permissive) · df403533c9480409 · report fixture: signature varables:list/1/str, ranges:list/1/list · returned list · level recorded 2026-09-26
get_base_conf configure_experiment/generate_configs.py ran MIT (permissive) · 87cf4755f4594737 · report fixture: signature base_config:str/0/str · returned dict · level recorded 2026-09-26
make_hashable utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · c17b6915065d3722 · report fixture: signature array:list/1/float · returned tuple · level recorded 2026-09-24
add_to_archive utils.py unverified MIT (permissive) · c005d4991ad325bd · report
cvt utils.py unverified MIT (permissive) · b97fcec4203f4736 · report
robintyh1/icml2021-pengqlambda community (archive-listed) 11 samples, 7 ran (5 instrument-failed) · 4 unverified
all_bools spinup/utils/run_utils.py ran · violated contract MIT recorded; this copy not marked cleared · pointer only · 2103e65a90ce7a04 · report fixture: signature vals:list/1/bool · returned bool · level recorded 2026-09-24
colorize in 60 papers spinup/utils/logx.py ran · our draft was wrong MIT recorded; this copy not marked cleared · pointer only · 7e36f1c357c4618d · report fixture: signature string:str/0/str, color:str/0/str, bold:bool/0/bool, highlight:bool/0/bool · returned str · level recorded 2026-09-24
convert_json in 11 papers spinup/utils/serialization_utils.py ran · our draft was wrong MIT recorded; this copy not marked cleared · pointer only · fbc505a5dac82646 · report fixture: signature obj:dict/0/? · returned dict · level recorded 2026-09-22
get_all_datasets in 8 papers spinup/utils/plot.py ran · our draft was wrong MIT recorded; this copy not marked cleared · pointer only · 62314e3b8ca6edfc · report fixture: signature all_logdirs:list/1/str, legend:list/1/str, select:NoneType/0/?, exclude:NoneType/0/? · returned list · level recorded 2026-09-24
get_datasets in 49 papers spinup/utils/plot.py ran · our draft was wrong MIT recorded; this copy not marked cleared · pointer only · e642bb98eca55069 · report fixture: signature logdir:str/0/str, condition:NoneType/0/? · returned list · level recorded 2026-09-24
is_json_serializable in 14 papers spinup/utils/serialization_utils.py ran · violated contract MIT recorded; this copy not marked cleared · pointer only · 9ca8b8e45f7fbebf · report fixture: signature v:dict/0/? · returned bool · level recorded 2026-09-22
valid_str in 5 papers spinup/utils/run_utils.py ran · our draft was wrong fingerprinted MIT recorded; this copy not marked cleared · pointer only · c6bdd181afa1fdf7 · report fixture: signature v:str/0/str · returned str · level recorded 2026-09-24
get_vars in 10 papers spinup/algos/tf1/td3_peng/core.py unverified MIT recorded; this copy not marked cleared · pointer only · a2580d7c4a763348 · report
mlp in 108 papers spinup/algos/tf1/td3_peng/core.py unverified MIT recorded; this copy not marked cleared · pointer only · e68b07bcdded00fa · report
placeholder in 7 papers spinup/algos/tf1/td3_peng/core.py unverified MIT recorded; this copy not marked cleared · pointer only · 17b03c462ce92576 · report
restore_tf_graph in 7 papers spinup/utils/logx.py unverified MIT recorded; this copy not marked cleared · pointer only · 8a70bbd1276e274c · report
yifan12wu/td3-jax community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
plot_fill plot.py ran MIT (permissive) · 986b521c8e695d46 · report fixture: signature x:ndarray/1/float, y:ndarray/1/float, yerr:ndarray/1/float, color:str/0/str, alpha_fill:float/0/float, ax:Axes/0/?, label:str/0/str, ls:str/0/str · returned Line2D · level recorded 2026-09-26
yydsok/oparl community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
split_list in 223 papers parell.py ran fingerprinted MIT (permissive) · 1dcf318473b1f057 · report fixture: signature input_list:list/1/int, K:int/0/int · returned list · level recorded 2026-09-26
tensormax TD3.py ran MIT (permissive) · 052527002e0be3dc · report fixture: signature targetQ:list/1/Tensor · returned Tensor · level recorded 2026-09-26
tensormin TD3.py ran MIT (permissive) · a8d4fda0f5e30ac7 · report fixture: returned Tensor · level recorded 2026-09-26

Tasks

Continuous ControlOpenAI GymQ-LearningReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Continuous Control Lunar Lander (OpenAI Gym) TD3 Score 277.26±4.17 #2 of 5 Archive leaderboard report
OpenAI Gym Ant-v4 TD3 Average Return 5942.55 #2 of 5 Archive leaderboard report
OpenAI Gym HalfCheetah-v4 TD3 Average Return 12026.73 #3 of 5 Archive leaderboard report
OpenAI Gym Hopper-v4 TD3 Average Return 3319.98 #2 of 5 Archive leaderboard report
OpenAI Gym Humanoid-v4 TD3 Average Return 198.44 #4 of 5 Archive leaderboard report
OpenAI Gym Walker2d-v4 TD3 Average Return 2612.74 #5 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: TD3, Target Policy Smoothing

AdamClipped Double Q-learningDense ConnectionsDouble Q-learningExperience ReplayReLUTD3Target Policy Smoothing

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