Papers › Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a...

Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor

4 Jan 2018ICML 2018 7arXiv:1801.01290archive 2025-07-28

Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, Sergey Levine

A platform for Applied Reinforcement Learning (Applied RL)

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

The archive's official repository (haarnoja/sac) was not harvested; the 148 samples below come from 27 community repositories.

Syntology 148 code samples harvested from 27 repositories linked to this paper: 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. Where Syntology's instrument failed: 17 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): 148 samples from 27 repositories, 91 ran (73 with no instrument failure; 18 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 28 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.

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

haarnoja/sac officialmentioned in papermentioned on GitHubtfNOASSERTIONSyntology: not harvested report
AmmarFayad/Behavioral-Actor-Critic mentioned on GitHubpytorchSyntology: not harvested report
AutumnWu/Streamlined-Off-Policy-Learning mentioned on GitHubtfSyntology: not harvested report
FOCAL-ICLR/FOCAL-ICLR mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric... (arXiv:2010.01112; that paper's own run record: 2 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; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
Kaixhin/imitation-learning mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
MarsEleven/car_racer_RL mentioned on GitHubpytorchSyntology: 7 samples, 3 ran (0 instrument-failed) · 4 unverified report
MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning mentioned on GitHubpytorchSyntology: 7 samples, 6 ran (0 instrument-failed) · 1 unverified report
MrSyee/pg-is-all-you-need mentioned on GitHubMITSyntology: not harvested report
QuentinVacher-rl/SoftActorCritic-in-Cpp-using-LibTorch mentioned on GitHubpytorchSyntology: not harvested report
RLAgent/state-marginal-matching mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Curiosity-driven Exploration by Self-supervised Prediction (arXiv:1705.05363; that paper's own run record: 16 ran (of which 9 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 1 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
Rafael1s/Deep-Reinforcement-Learning-Udacity mentioned on GitHubpytorchSyntology: 6 samples, 3 ran (0 instrument-failed) · 3 unverified report
SaminYeasar/off_policy_ac mentioned on GitHubpytorchSyntology: 6 samples, 5 ran (2 instrument-failed) · 1 unverified report
ShawK91/Evolutionary-Reinforcement-Learning mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
ShawK91/erl_paper_nips18 mentioned on GitHubpytorchSyntology: not harvested report
Steinheilig/Imbiss mentioned on GitHubSyntology: not harvested report
X3N4/car_racer mentioned on GitHubpytorchSyntology: not harvested report
ac-93/soft-actor-critic mentioned on GitHubtfSyntology: 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
ajaysub110/rl-pytorch mentioned on GitHubpytorchSyntology: 7 samples, 2 ran (0 instrument-failed) · 5 unverified 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
autumnwu/aggressive-q-learning-with-ensembles mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
baturaysaglam/la3p mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified 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
cindycia/Atari-SAC-Discrete mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Soft Actor-Critic for Discrete Action Settings (arXiv:1910.07207; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
core-robotics-lab/icct mentioned on GitHubpytorchMITSyntology: not harvested report
dasgringuen/assetto_corsa_gym mentioned on GitHubpytorchMITSyntology: 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); nothing checks that they implement this paper's method. report
dfki-ric-underactuated-lab/torque_limited_simple_pendulum 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
donamin/llc mentioned on GitHubtfSyntology: 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
flowersteam/rl_stats mentioned on GitHubSyntology: not harvested report
garyzyr001/rethinking-airl mentioned on GitHubpytorchSyntology: 8 samples, 4 ran (0 instrument-failed) · 4 unverified report
gijskoning/ReproducingCURL mentioned on GitHubpytorchSyntology: not harvested report
h-aboutalebi/SparceReward mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
hyunin-lee/ForecasterSAC mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
ikostrikov/jax-rl mentioned on GitHubjaxSyntology: 4 samples, 0 ran · 4 unverified report
kairproject/kair_algorithms_draft mentioned on GitHubpytorchSyntology: not harvested report
kdally/fault-tolerant-flight-control-drl mentioned on GitHubSyntology: 10 samples, 8 ran (6 instrument-failed) · 2 unverified report
ku2482/discor.pytorch mentioned on GitHubpytorchSyntology: 11 samples, 4 ran (1 instrument-failed) · 7 unverified report
ku2482/gail-airl-ppo.pytorch mentioned on GitHubpytorchSyntology: 5 samples, 2 ran (0 instrument-failed) · 3 unverified report
ku2482/rljax mentioned on GitHubjaxMITSyntology: not harvested report
ku2482/rltorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Soft Actor-Critic for Discrete Action Settings (arXiv:1910.07207; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
ku2482/soft-actor-critic.pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Dropout Q-Functions for Doubly Efficient Reinforcement Learning (arXiv:2110.02034; that paper's own run record: 6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
kushagra06/SAC mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
lanqingli1993/focal-iclr mentioned on GitHubpytorchSyntology: not harvested report
learn-to-race/l2r mentioned on GitHubGPL-2.0Syntology: not harvested report
lollcat/Soft-Actor-Critic mentioned on GitHubtfSyntology: not harvested report
lucadellalib/sac-beta mentioned on GitHubpytorchApache-2.0Syntology: not harvested 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
moreanp/csro mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Context Shift Reduction for Offline Meta-Reinforcement Learning (arXiv:2311.03695; that paper's own run record: 4 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; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mxblr/DeepRLHockey mentioned on GitHubtfSyntology: not harvested report
nagisazj/idaq_public mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Offline Meta Reinforcement Learning with In-Distribution Online Adaptation (arXiv:2305.19529; 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) · 1 unverified); nothing checks that they implement this paper's method. report
polixir/NeoRL mentioned on GitHubSyntology: not harvested report
pranz24/pytorch-soft-actor-critic mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
quantumiracle/Popular-RL-Algorithms mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
rk1998/robot-sac mentioned on GitHubtfSyntology: not harvested report
roythuly/obac mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
sunfex/weighted-sac mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
susan-amin/SparseBaseline1 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
tarod13/SAC mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
thomashirtz/pytorch-soft-actor-critic mentioned on GitHubpytorchMITSyntology: 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
thomashirtz/soft-actor-critic mentioned on GitHubpytorchSyntology: 12 samples, 7 ran (3 instrument-failed) · 5 unverified report
tilkb/thermoai 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) and 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); nothing checks that they implement this paper's method. report
timoklein/car_racer mentioned on GitHubpytorchSyntology: not harvested report
tliu1997/rnac mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation (arXiv:2307.08875; that paper's own run record: 11 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
tmjeong1103/RL_with_RAY mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (1 instrument-failed) · 0 unverified report
toshikwa/discor.pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction (arXiv:2003.07305; 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) · 1 unverified); nothing checks that they implement this paper's method. report
toshikwa/soft-actor-critic.pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent (arXiv:2605.21282; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 6 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
trackmania-rl/tmrl mentioned on GitHubpytorchSyntology: not harvested report
watchernyu/spinningup-drl-prototyping mentioned on GitHubtfSyntology: 6 samples, 2 ran (0 instrument-failed) · 4 unverified report
yhisaki/average-reward-drl mentioned on GitHubpytorchSyntology: 13 samples, 10 ran (3 instrument-failed) · 3 unverified report
yimingpeng/sac-master mentioned on GitHubtfSyntology: not harvested report
yining043/SAC-discrete mentioned on GitHubtfSyntology: not harvested report
BY571/Soft-Actor-Critic-and-Extensions pytorchSyntology: 10 samples, 9 ran (1 instrument-failed) · 1 unverified 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
Ipsedo/EvoMotion pytorchSyntology: not harvested report
facebookresearch/rl jaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark (arXiv:2306.17100; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 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
ray-project/ray Syntology: not harvested report
seungju-k1m/sac-td3-td7 pytorchSyntology: not harvested report
tensorlayer/RLzoo tfSyntology: 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
toni-sm/skrl jaxMITSyntology: not harvested report
xiuyu0000/new_papers_codes mindsporeSyntology: 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

148 samples harvested: 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. “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.

3ran · honoured contract
1ran · violated contract
17ran · our draft was wrong
1ran; the contract check could not run
69ran
57unverified

Licence: 66 of the 148 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 27 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 20 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.

Kaixhin/imitation-learning community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
SoftActor models.py ran · metamorphic tier: deterministic MIT (permissive) · b473c449b3da39cc · report fixture: returned SoftActor · level recorded 2026-09-22
_create_fcnn models.py ran · our draft was wrong MIT (permissive) · b7fc01f37cbb0eb1 · report fixture: signature input_size:int/0/int, hidden_size:int/0/int, depth:int/0/int, output_size:int/0/int, activation_function:str/0/str, input_dropout:float/0/float, dropout:float/0/float, final_gain:float/0/float, spectral_norm:bool/0/bool · returned Sequential · level recorded 2026-09-22
MarsEleven/car_racer_RL community (archive-listed) 7 samples, 3 ran (0 instrument-failed) · 4 unverified
DeterministicPolicy sac/sac.py ran fingerprinted no licence file found · pointer only · d4dfbbf39952f704 · report fixture: returned DeterministicPolicy · level recorded 2026-09-22
GaussianPolicy in 7 papers sac/sac.py ran fingerprinted no licence file found · pointer only · 57c7562fda9bbab3 · report fixture: returned GaussianPolicy · level recorded 2026-09-22
QNetwork in 11 papers sac/sac.py ran no licence file found · pointer only · e3aca820c0049604 · report fixture: returned QNetwork · level recorded 2026-09-22
SAC in 8 papers sac/sac.py unverified no licence file found · pointer only · fa07dbb92f6c222b · report
hard_update sac/sac.py unverified no licence file found · pointer only · 1adf91cc413cf6c2 · report
soft_update in 8 papers sac/sac.py unverified no licence file found · pointer only · ace24484ab1d6b7f · report
weights_init_ sac/sac.py unverified no licence file found · pointer only · abe2b5a0b5e817fd · report
MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning community (archive-listed) 7 samples, 6 ran (0 instrument-failed) · 1 unverified
Actor in 68 papers src/agents.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · de5e64dc2bfc6a33 · report fixture: returned Actor · level recorded 2026-09-22
Agent_ManualTemperature src/agents.py ran Apache-2.0 (permissive) · 0918147b61a18074 · report fixture: returned Agent_ManualTemperature · level recorded 2026-09-22
Critic in 60 papers src/agents.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 7c4433b21cf61a2c · report fixture: returned Critic · level recorded 2026-09-22
Network in 40 papers src/agents.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · de764e9177884a12 · report fixture: returned Network · level recorded 2026-09-22
ReplayBuffer in 33 papers src/agents.py ran Apache-2.0 (permissive) · ac5ecca5b7705f8a · report fixture: returned ReplayBuffer · level recorded 2026-09-22
Value in 10 papers src/agents.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · f8845c35735f20bc · report fixture: returned Value · level recorded 2026-09-22
Agent in 42 papers src/agents.py unverified Apache-2.0 (permissive) · b0e759b2d521e146 · report
Rafael1s/Deep-Reinforcement-Learning-Udacity community (archive-listed) 6 samples, 3 ran (0 instrument-failed) · 3 unverified
GaussianPolicy in 7 papers Ant-PyBulletEnv-Soft-Actor-Critic/sac_agent.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · bf0d89394b22e1b6 · report fixture: returned GaussianPolicy · level recorded 2026-09-22
QNetwork in 11 papers Ant-PyBulletEnv-Soft-Actor-Critic/sac_agent.py ran · metamorphic tier: deterministic no licence file found · pointer only · f37748964b0cd7da · report fixture: returned QNetwork · level recorded 2026-09-22
soft_actor_critic_agent Ant-PyBulletEnv-Soft-Actor-Critic/sac_agent.py ran no licence file found · pointer only · 3a0835e6ce008741 · report fixture: returned soft_actor_critic_agent · level recorded 2026-09-22
hard_update Ant-PyBulletEnv-Soft-Actor-Critic/sac_agent.py unverified no licence file found · pointer only · 799c08d64f58d9ef · report
soft_update in 8 papers Ant-PyBulletEnv-Soft-Actor-Critic/sac_agent.py unverified no licence file found · pointer only · f735812881238a1f · report
weights_init_ Ant-PyBulletEnv-Soft-Actor-Critic/sac_agent.py unverified no licence file found · pointer only · 0537c4bc8300d410 · report
SaminYeasar/off_policy_ac community (archive-listed) 6 samples, 5 ran (2 instrument-failed) · 1 unverified
Actor in 68 papers SAC/SAC.py ran fingerprinted no licence file found · pointer only · dc01224a73ea8148 · report fixture: returned Actor · level recorded 2026-09-22
Critic in 60 papers SAC/SAC.py ran no licence file found · pointer only · a0a4c6c892e497cd · report fixture: returned Critic · level recorded 2026-09-22
SAC in 8 papers SAC/SAC.py ran no licence file found · pointer only · 43d63d9b3b6240a1 · report fixture: returned SAC · level recorded 2026-09-22
apply_squashing_func SAC/SAC.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 52028903a218ba91 · report fixture: signature mu:Tensor/2/float, pi:Tensor/2/float, log_pi:Tensor/2/float · returned tuple · level recorded 2026-09-22
gaussian_likelihood in 6 papers SAC/SAC.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 958cab9f3ba6af81 · report fixture: signature noise:Tensor/2/float, log_std:Tensor/2/float · returned Tensor · level recorded 2026-09-22
weight_init in 73 papers SAC/SAC.py unverified no licence file found · pointer only · 68c08ef9d5d473a7 · report
ShawK91/Evolutionary-Reinforcement-Learning community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
SAC in 8 papers algos/sac.py ran no licence file found · pointer only · 217cd7f6f86864da · report fixture: returned SAC · level recorded 2026-09-22
hard_update algos/sac.py unverified no licence file found · pointer only · 7abe222eb3afeb6f · report
soft_update in 8 papers algos/sac.py unverified no licence file found · pointer only · fcdeb82694a504e1 · report
ajaysub110/rl-pytorch community (archive-listed) 7 samples, 2 ran (0 instrument-failed) · 5 unverified
PolicyNetwork in 7 papers sac/models/soft_actor_critic.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · ec7050db6c32a43a · report fixture: signature s:Tensor/2/float · returned tuple · level recorded 2026-09-22
QNetwork in 11 papers sac/models/soft_actor_critic.py ran · metamorphic tier: invariant no licence file found · pointer only · e182a5c8f1d1e16f · report fixture: signature s:Tensor/2/float, a:Tensor/2/float · returned Tensor · level recorded 2026-09-22
ReplayMemory in 11 papers sac/models/soft_actor_critic.py unverified no licence file found · pointer only · 995a5d6382ee476d · report
SoftActorCritic sac/models/soft_actor_critic.py unverified no licence file found · pointer only · ecf34b65e8d9d3bb · report
copy_params in 6 papers sac/models/soft_actor_critic.py unverified no licence file found · pointer only · d1076220e33b55ba · report
init_weights in 109 papers sac/models/soft_actor_critic.py unverified no licence file found · pointer only · 8576d4b41e6ed12f · report
soft_update in 8 papers sac/models/soft_actor_critic.py unverified no licence file found · pointer only · 54ab8d446018b958 · report
autumnwu/aggressive-q-learning-with-ensembles community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
TanhGaussianPolicySACAdapt spinup/algos/aqe/core_aqe.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · f552f5cc13186908 · report fixture: signature obs:Tensor/2/float, deterministic:bool/0/bool, return_log_prob:bool/0/bool · returned tuple · level recorded 2026-09-22
baturaysaglam/la3p community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
Critic in 60 papers Code/SAC/SAC.py ran · metamorphic tier: deterministic MIT (permissive) · f8ead4c2c205ecd8 · report fixture: returned Critic · level recorded 2026-09-22
DeterministicPolicy Code/SAC/SAC.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 7553f61c31debefb · report fixture: returned DeterministicPolicy · level recorded 2026-09-22
GaussianPolicy in 7 papers Code/SAC/SAC.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 152bc1e449547d23 · report fixture: returned GaussianPolicy · level recorded 2026-09-22
SAC in 8 papers Code/SAC/SAC.py unverified MIT (permissive) · 0edd4b0f90be8f84 · report
garyzyr001/rethinking-airl community (archive-listed) 8 samples, 4 ran (0 instrument-failed) · 4 unverified
Buffer in 23 papers airl/algo/sac.py ran no licence file found · pointer only · 94573a894a42ebff · report fixture: returned Buffer · level recorded 2026-09-22
SerializedBuffer airl/algo/sac.py ran no licence file found · pointer only · c74fba5d30037b69 · report fixture: returned SerializedBuffer · level recorded 2026-09-22
StateDependentPolicy airl/algo/sac.py ran fingerprinted no licence file found · pointer only · f0f9d0b00b3e9632 · report fixture: returned StateDependentPolicy · level recorded 2026-09-22
TwinnedStateActionFunction airl/algo/sac.py ran no licence file found · pointer only · e42d91ba746c3a14 · report fixture: returned TwinnedStateActionFunction · level recorded 2026-09-22
Algorithm in 26 papers airl/algo/sac.py unverified no licence file found · pointer only · 803d90cd603ff8c0 · report
SAC in 8 papers airl/algo/sac.py unverified no licence file found · pointer only · 6af70c8a2239d7c5 · report
disable_gradient airl/algo/sac.py unverified no licence file found · pointer only · ed542fae5c7f2c04 · report
soft_update in 8 papers airl/algo/sac.py unverified no licence file found · pointer only · 8dc0540b8dfe9b97 · report
h-aboutalebi/SparceReward community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
AbstractAgent in 5 papers engine/algorithms/SAC/sac.py ran no licence file found · pointer only · 424bf06f8d8eb998 · report fixture: returned AbstractAgent · level recorded 2026-09-22
DeterministicPolicy engine/algorithms/SAC/sac.py ran fingerprinted no licence file found · pointer only · 3faeea6e22edd34d · report fixture: returned DeterministicPolicy · level recorded 2026-09-22
GaussianPolicy in 7 papers engine/algorithms/SAC/sac.py ran fingerprinted no licence file found · pointer only · 8ee15fddb3528e86 · report fixture: returned GaussianPolicy · level recorded 2026-09-22
SAC in 8 papers engine/algorithms/SAC/sac.py unverified no licence file found · pointer only · 9e2e2c85eabbd88f · report
hyunin-lee/ForecasterSAC community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
compute_weight_X sac.py ran · honoured contract fingerprinted MIT (permissive) · a2697a9ea209c680 · report fixture: signature past_length:int/0/int · returned Tensor · level recorded 2026-09-22
SAC in 8 papers sac.py unverified MIT (permissive) · 9efbd1e63c6644e5 · report
ikostrikov/jax-rl community (archive-listed) 4 samples, 0 ran · 4 unverified
Model in 227 papers jaxrl/agents/sac/sac_learner.py unverified MIT (permissive) · 3ef56075bad93ec9 · report
SACLearner jaxrl/agents/sac/sac_learner.py unverified MIT (permissive) · 6bc96035de025e83 · report
_update_jit jaxrl/agents/sac/sac_learner.py unverified MIT (permissive) · f07528bc5e071757 · report
target_update in 9 papers jaxrl/agents/sac/sac_learner.py unverified MIT (permissive) · f62b5d3c6983e5aa · report
kdally/fault-tolerant-flight-control-drl community (archive-listed) 10 samples, 8 ran (6 instrument-failed) · 2 unverified
ReplayBuffer in 33 papers fault_tolerant_flight_control_drl/agent/sac.py ran MIT (permissive) · 8119b0afbe2d940e · report fixture: returned ReplayBuffer · level recorded 2026-09-22
bytes_to_params fault_tolerant_flight_control_drl/agent/sac.py ran · our draft was wrong MIT (permissive) · fa8517ef05057c7f · report fixture: signature serialized_params:bytes/0/?, param_list:list/1/str · returned OrderedDict · level recorded 2026-09-22
data_to_json fault_tolerant_flight_control_drl/agent/sac.py ran · our draft was wrong MIT (permissive) · 36b66092679a3132 · report fixture: signature data:dict/0/? · returned str · level recorded 2026-09-22
is_json_serializable in 14 papers fault_tolerant_flight_control_drl/agent/sac.py ran · violated contract MIT (permissive) · c70b5621a0ca8047 · report fixture: signature item:dict/0/? · returned bool · level recorded 2026-09-22
json_to_data fault_tolerant_flight_control_drl/agent/sac.py ran · our draft was wrong MIT (permissive) · ad86f46cc9af956b · report fixture: signature json_string:str/0/str, custom_objects:dict/0/? · returned dict · level recorded 2026-09-22
params_to_bytes fault_tolerant_flight_control_drl/agent/sac.py ran · our draft was wrong MIT (permissive) · 1d75daad61f15424 · report fixture: signature params:dict/0/? · returned bytes · level recorded 2026-09-22
scale_action fault_tolerant_flight_control_drl/agent/sac.py ran · our draft was wrong MIT (permissive) · 4a486e5048778576 · report fixture: signature action_space:Box/1/float, action:ndarray/1/float · returned ndarray · level recorded 2026-09-22
unscale_action fault_tolerant_flight_control_drl/agent/sac.py ran · our draft was wrong MIT (permissive) · 5a4d3fd6b28ecaf4 · report fixture: signature action_space:Box/1/float, scaled_action:ndarray/1/float · returned ndarray · level recorded 2026-09-22
SAC in 8 papers fault_tolerant_flight_control_drl/agent/sac.py unverified MIT (permissive) · 569d921eb9b51536 · report
set_global_seeds fault_tolerant_flight_control_drl/agent/sac.py unverified MIT (permissive) · 0dfad75cd2d202d6 · report
ku2482/discor.pytorch community (archive-listed) 11 samples, 4 ran (1 instrument-failed) · 7 unverified
GaussianPolicy in 7 papers discor/algorithm/sac.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 8761dc745b44dc04 · report fixture: returned GaussianPolicy · level recorded 2026-09-22
StateActionFunction discor/algorithm/sac.py ran · metamorphic tier: deterministic MIT (permissive) · b1e066bc1ff4b61b · report fixture: returned StateActionFunction · level recorded 2026-09-22
TwinnedStateActionFunction discor/algorithm/sac.py ran · metamorphic tier: deterministic MIT (permissive) · 5d13132d2e3c5ef0 · report fixture: returned TwinnedStateActionFunction · level recorded 2026-09-22
create_linear_network discor/algorithm/sac.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) · 248f63c9cf4d972e · 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/?, initializer:callable/0/? · returned Sequential · level recorded 2026-09-22
Algorithm in 26 papers discor/algorithm/sac.py unverified MIT (permissive) · eaf547baf5f33e43 · report
BaseNetwork in 19 papers discor/algorithm/sac.py unverified MIT (permissive) · d6d4b5a5d84ba8ad · report
SAC in 8 papers discor/algorithm/sac.py unverified MIT (permissive) · 348b1924f106de50 · report
_soft_update discor/algorithm/sac.py unverified MIT (permissive) · 231f633be51bd617 · report
assert_action discor/algorithm/sac.py unverified MIT (permissive) · ded76544fe9d6607 · report
initialize_weights_xavier discor/algorithm/sac.py unverified MIT (permissive) · 544fe1f08a36cc62 · report
soft_update in 8 papers discor/algorithm/sac.py unverified MIT (permissive) · e8abbe917721f0c8 · report
ku2482/gail-airl-ppo.pytorch community (archive-listed) 5 samples, 2 ran (0 instrument-failed) · 3 unverified
SerializedBuffer gail_airl_ppo/algo/sac.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · eb9bc09b3ca641cb · report fixture: signature batch_size:int/0/int · returned tuple · level recorded 2026-09-22
StateDependentPolicy gail_airl_ppo/algo/sac.py ran fingerprinted MIT (permissive) · 77baa7a1a168fc24 · report fixture: signature states:Tensor/2/float · returned Tensor · level recorded 2026-09-24
Algorithm in 26 papers gail_airl_ppo/algo/sac.py unverified MIT (permissive) · ff7a80131e64a08d · report
Buffer in 23 papers gail_airl_ppo/algo/sac.py unverified MIT (permissive) · b6b1a23b07a627dd · report
SAC in 8 papers gail_airl_ppo/algo/sac.py unverified MIT (permissive) · 104ef2d3e37baa21 · report
kushagra06/SAC community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
SACActor model.py ran · metamorphic tier: deterministic no licence file found · pointer only · e5d43066162708ff · report fixture: returned SACActor · level recorded 2026-09-22
RLNetwork model.py unverified no licence file found · pointer only · b36d35fd411b0150 · report
pranz24/pytorch-soft-actor-critic community (archive-listed) 1 sample, 0 ran · 1 unverified
SAC in 8 papers sac.py unverified MIT (permissive) · d77f61cb28da8383 · report
quantumiracle/Popular-RL-Algorithms community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
PolicyNetwork in 7 papers sac_v2.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 540316788d2c30c7 · report fixture: returned PolicyNetwork · level recorded 2026-09-22
ReplayBuffer in 33 papers sac_v2.py ran Apache-2.0 (permissive) · 70249df825c62d7e · report fixture: returned ReplayBuffer · level recorded 2026-09-22
SoftQNetwork sac_v2.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 0688d4da92feee38 · report fixture: returned SoftQNetwork · level recorded 2026-09-22
SAC_Trainer sac_v2.py unverified Apache-2.0 (permissive) · 3e1e70dd1d5f3958 · report
roythuly/obac community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
GaussianPolicy in 7 papers model/algo.py ran fingerprinted no licence file found · pointer only · da8ebd6e9ea11fca · report fixture: returned GaussianPolicy · level recorded 2026-09-22
QNetwork in 11 papers model/algo.py ran no licence file found · pointer only · 0d80189fd77d3aa6 · report fixture: returned QNetwork · level recorded 2026-09-22
ValueNetwork in 6 papers model/algo.py ran fingerprinted no licence file found · pointer only · 18ecb1311366b8cb · report fixture: signature state:Tensor/2/float · returned Tensor · level recorded 2026-09-24
OBAC model/algo.py unverified no licence file found · pointer only · 7524ef9f7598dd6f · report
sunfex/weighted-sac community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
BaseQNet sac.py ran MIT (permissive) · d6b54769dcaa3ec5 · report fixture: returned BaseQNet · level recorded 2026-09-22
BatchQNet sac.py ran MIT (permissive) · e6f3bef6186ec524 · report fixture: returned BatchQNet · level recorded 2026-09-22
GaussianPolicy in 7 papers sac.py ran fingerprinted MIT (permissive) · 5722a85a4a153169 · report fixture: returned GaussianPolicy · level recorded 2026-09-22
SAC in 8 papers sac.py unverified MIT (permissive) · 1cb5a8aa4ee6cb43 · report
tarod13/SAC community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
policyNet nets.py ran · metamorphic tier: deterministic no licence file found · pointer only · 642892e9419a125d · report fixture: signature s:Tensor/2/float · returned tuple · level recorded 2026-09-22
thomashirtz/soft-actor-critic community (archive-listed) 12 samples, 7 ran (3 instrument-failed) · 5 unverified
QNetwork in 11 papers soft_actor_critic/agent.py ran MIT (permissive) · b7030d8d56cd639a · report fixture: returned QNetwork · level recorded 2026-09-22
ReplayBuffer in 33 papers soft_actor_critic/agent.py ran MIT (permissive) · 0020d85f4dbfb10b · report fixture: returned ReplayBuffer · level recorded 2026-09-22
StochasticPolicy soft_actor_critic/agent.py ran fingerprinted MIT (permissive) · 7e61ac4f70c90628 · report fixture: returned StochasticPolicy · level recorded 2026-09-22
TwinnedQNetworks soft_actor_critic/agent.py ran MIT (permissive) · 5b2e9a4c85bbab7d · report fixture: returned TwinnedQNetworks · level recorded 2026-09-22
eval_mode soft_actor_critic/agent.py ran · our draft was wrong MIT (permissive) · 298e84cf1d9ed36c · report fixture: signature net:callable/0/? · returned _GeneratorContextManager · level recorded 2026-09-22
get_device in 101 papers soft_actor_critic/agent.py ran · our draft was wrong MIT (permissive) · d4978950888874f4 · report fixture: signature overwrite:NoneType/0/?, device:str/0/str, fallback_device:str/0/str · returned device · level recorded 2026-09-22
get_multilayer_perceptron soft_actor_critic/agent.py ran · our draft was wrong MIT (permissive) · 1afbe631504fbaf7 · report fixture: signature unit_list:list/1/int, keep_last_relu:bool/0/bool · returned Sequential · level recorded 2026-09-22
Agent in 42 papers soft_actor_critic/agent.py unverified MIT (permissive) · 05437b66f08eb4d6 · report
load_model in 479 papers soft_actor_critic/agent.py unverified MIT (permissive) · 706459e26fbb0b4c · report
save_model in 19 papers soft_actor_critic/agent.py unverified MIT (permissive) · 7d297778525c40d1 · report
update_network_parameters soft_actor_critic/agent.py unverified MIT (permissive) · 85fff8ae028fc1dd · report
weight_initialization soft_actor_critic/agent.py unverified MIT (permissive) · 6ae1b395aeb4e7d3 · report
tmjeong1103/RL_with_RAY community (archive-listed) 4 samples, 4 ran (1 instrument-failed) · 0 unverified
MLPActorCritic SAC_RAY/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · a830c8ece63f9c57 · report fixture: returned MLPActorCritic · level recorded 2026-09-22
MLPGaussianPolicy SAC_RAY/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · c02fc6e11c3ba5cf · report fixture: returned MLPGaussianPolicy · level recorded 2026-09-22
MLPQFunction SAC_RAY/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 14211bf5685457cf · report fixture: returned MLPQFunction · level recorded 2026-09-22
mlp in 108 papers SAC_RAY/model.py ran · our draft was wrong no licence file found · pointer only · a1e9dc4773ffeba5 · report fixture: signature odim:int/0/int, hdims:list/1/int, actv:callable/0/?, output_actv:NoneType/0/? · returned Sequential · level recorded 2026-09-22
watchernyu/spinningup-drl-prototyping community (archive-listed) 6 samples, 2 ran (0 instrument-failed) · 4 unverified
clip_but_pass_gradient spinup/algos/sac/core.py ran · honoured contract fingerprinted MIT (permissive) · 4731ca1d377b8284 · report fixture: signature x:EagerTensor/2/float, l:float/0/float, u:float/0/float · returned EagerTensor · level recorded 2026-09-22
gaussian_likelihood in 6 papers spinup/algos/sac/core.py ran · honoured contract fingerprinted MIT (permissive) · 5c26c93931dce503 · report fixture: signature x:EagerTensor/2/float, mu:EagerTensor/2/float, log_std:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
apply_squashing_func spinup/algos/sac/core.py unverified MIT (permissive) · 198be549ce9696ef · report
mlp in 108 papers spinup/algos/sac/core.py unverified MIT (permissive) · e68b07bcdded00fa · report
mlp_actor_critic spinup/algos/sac/core.py unverified MIT (permissive) · 8498689f07030ac8 · report
mlp_gaussian_policy spinup/algos/sac/core.py unverified MIT (permissive) · a860fee8188a0218 · report
yhisaki/average-reward-drl community (archive-listed) 13 samples, 10 ran (3 instrument-failed) · 3 unverified
Batch in 5 papers average_reward_drl/algorithms/sac.py ran no licence file found · pointer only · 6bb425a4771dc88f · report fixture: returned Batch · level recorded 2026-09-22
ConcatStateAction average_reward_drl/algorithms/sac.py ran no licence file found · pointer only · c10734f04f231cb4 · report fixture: signature state_action:tuple/1/Tensor · returned Tensor · level recorded 2026-09-24
Logger in 25 papers average_reward_drl/algorithms/sac.py ran no licence file found · pointer only · 4aec8353051fa16d · report fixture: returned Logger · level recorded 2026-09-22
MultiLinear average_reward_drl/algorithms/sac.py ran · metamorphic tier: deterministic no licence file found · pointer only · 5d3a98fbf8446e0c · report fixture: returned MultiLinear · level recorded 2026-09-22
ReplayBuffer in 33 papers average_reward_drl/algorithms/sac.py ran no licence file found · pointer only · e9664791458e5ade · report fixture: returned ReplayBuffer · level recorded 2026-09-22
ScalarHolder average_reward_drl/algorithms/sac.py ran · metamorphic tier: deterministic no licence file found · pointer only · 33ec92b652664841 · report fixture: returned ScalarHolder · level recorded 2026-09-22
SquashedDiagonalGaussianHead average_reward_drl/algorithms/sac.py ran · metamorphic tier: deterministic no licence file found · pointer only · 02a45597a277afab · report fixture: returned SquashedDiagonalGaussianHead · level recorded 2026-09-22
convert_to_tensor in 10 papers average_reward_drl/algorithms/sac.py ran · our draft was wrong no licence file found · pointer only · cdf94e91c8746537 · report fixture: signature arr:ndarray/2/float, device:str/0/str, dtype:dtype/0/? · returned Tensor · level recorded 2026-09-22
group_by_keys average_reward_drl/algorithms/sac.py ran · our draft was wrong no licence file found · pointer only · 1dd9b9ae9fa9426f · report fixture: signature lst:list/1/dict, use_all_keys:bool/0/bool · returned dict · level recorded 2026-09-22
ortho_init in 12 papers average_reward_drl/algorithms/sac.py ran · our draft was wrong no licence file found · pointer only · 5c5bce3523ed4d69 · report fixture: signature layer:callable/0/?, gain:float/0/float · returned Linear · level recorded 2026-09-22
AlgorithmBase average_reward_drl/algorithms/sac.py unverified no licence file found · pointer only · 110041979f3c0cb8 · report
SAC in 8 papers average_reward_drl/algorithms/sac.py unverified no licence file found · pointer only · 4849ba61ae47dd70 · report
polyak_update average_reward_drl/algorithms/sac.py unverified no licence file found · pointer only · f299a2900b4034fa · report
BY571/Soft-Actor-Critic-and-Extensions community (archive-listed) 10 samples, 9 ran (1 instrument-failed) · 1 unverified
Actor in 68 papers files/Agent.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 5d8f81c210a0aacb · report fixture: returned Actor · level recorded 2026-09-22
Critic in 60 papers files/Agent.py ran · metamorphic tier: deterministic MIT (permissive) · 8f0377d2cad944f3 · report fixture: returned Critic · level recorded 2026-09-22
DeepActor files/Agent.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 9ee95d5b4fc2dd44 · report fixture: returned DeepActor · level recorded 2026-09-22
DeepCritic files/Agent.py ran · metamorphic tier: deterministic MIT (permissive) · a57bb45ab6a0bc51 · report fixture: returned DeepCritic · level recorded 2026-09-22
DeepIQN files/Agent.py ran · metamorphic tier: deterministic MIT (permissive) · 693c33a1aa6474c6 · report fixture: returned DeepIQN · level recorded 2026-09-22
IQN files/Agent.py ran · metamorphic tier: deterministic MIT (permissive) · 94a135edcb95baf2 · report fixture: returned IQN · level recorded 2026-09-22
PrioritizedReplay files/Agent.py ran MIT (permissive) · 91bcdaabd64f8eee · report fixture: returned PrioritizedReplay · level recorded 2026-09-22
ReplayBuffer in 33 papers files/Agent.py ran MIT (permissive) · a6c39d1200737d3f · report fixture: returned ReplayBuffer · level recorded 2026-09-22
calculate_huber_loss in 5 papers files/Agent.py ran · our draft was wrong MIT (permissive) · d9d455622c2dcd61 · report fixture: signature td_errors:Tensor/3/float, k:float/0/float · returned Tensor · level recorded 2026-09-22
Agent in 42 papers files/Agent.py unverified MIT (permissive) · 2ae117303c9ac594 · 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.

27 assemblies on this paper: 27 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

27 sibling assemblies for soft actor-critic (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 27 sibling assemblies; the other 15 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for soft actor-critic (graph method: soft actor-critic). 7 bricks; individually on a fixture: 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) · 1 unverified; every one of the 6 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 27 siblings

  1. Agent_ManualTemperature entry · level 1 · ran · 0918147b61a18074
  2. Agent helper · level 0 · unverified · b0e759b2d521e146
  3. Critic model · level 1 · ran · 7c4433b21cf61a2c
  4. Value helper · level 1 · ran · f8845c35735f20bc
  5. Actor model · level 1 · ran · de5e64dc2bfc6a33
  6. ReplayBuffer sampler · level 1 · ran · ac5ecca5b7705f8a
  7. Network helper · level 1 · ran · de764e9177884a12

harvested Assembly for soft actor-critic (graph method: soft actor-critic). 6 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) · 3 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 27 siblings

  1. soft_actor_critic_agent entry · level 1 · ran · 3a0835e6ce008741
  2. GaussianPolicy model · level 1 · ran · bf0d89394b22e1b6
  3. QNetwork model · level 1 · ran · f37748964b0cd7da
  4. hard_update update_rule · level 0 · unverified · 799c08d64f58d9ef
  5. soft_update update_rule · level 0 · unverified · f735812881238a1f
  6. weights_init_ helper · level 0 · unverified · 0537c4bc8300d410

harvested Assembly for soft actor-critic (graph method: soft actor-critic). 10 bricks; individually on a fixture: 8 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 27 siblings

  1. SAC entry · level 0 · unverified · 569d921eb9b51536
  2. ReplayBuffer sampler · level 1 · ran · 8119b0afbe2d940e
  3. bytes_to_params helper · level 1 · ran · our draft was wrong · fa8517ef05057c7f
  4. data_to_json helper · level 1 · ran · our draft was wrong · 36b66092679a3132
  5. json_to_data helper · level 1 · ran · our draft was wrong · ad86f46cc9af956b
  6. params_to_bytes helper · level 1 · ran · our draft was wrong · 1d75daad61f15424
  7. scale_action helper · level 1 · ran · our draft was wrong · 4a486e5048778576
  8. set_global_seeds helper · level 0 · unverified · 0dfad75cd2d202d6
  9. unscale_action helper · level 1 · ran · our draft was wrong · 5a4d3fd6b28ecaf4
  10. is_json_serializable helper · level 1 · ran · violated contract · c70b5621a0ca8047

harvested Assembly for soft actor-critic (graph method: soft actor-critic). 7 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) · 4 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 27 siblings

  1. SAC entry · level 0 · unverified · 0edd4b0f90be8f84
  2. Critic model · level 1 · ran · f8ead4c2c205ecd8
  3. DeterministicPolicy model · level 1 · ran · 7553f61c31debefb
  4. GaussianPolicy model · level 1 · ran · 152bc1e449547d23
  5. hard_update update_rule · level 0 · unverified · 799c08d64f58d9ef
  6. soft_update update_rule · level 0 · unverified · f735812881238a1f
  7. weights_init_ helper · level 0 · unverified · 0537c4bc8300d410

harvested Assembly for soft actor-critic (graph method: soft actor-critic). 11 bricks; individually on a fixture: 10 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 27 siblings

  1. Agent entry · level 0 · unverified · 2ae117303c9ac594
  2. Actor model · level 1 · ran · 5d8f81c210a0aacb
  3. Critic model · level 1 · ran · 8f0377d2cad944f3
  4. DeepActor helper · level 1 · ran · 9ee95d5b4fc2dd44
  5. DeepCritic helper · level 1 · ran · a57bb45ab6a0bc51
  6. DeepIQN helper · level 1 · ran · 693c33a1aa6474c6
  7. IQN helper · level 1 · ran · 94a135edcb95baf2
  8. PrioritizedReplay helper · level 1 · ran · 91bcdaabd64f8eee
  9. ReplayBuffer helper · level 1 · ran · a6c39d1200737d3f
  10. calculate_huber_loss loss · level 1 · ran · our draft was wrong · d9d455622c2dcd61
  11. hidden_init helper · level 1 · ran · honoured contract · 24ee38e114b38bce

harvested Assembly for soft actor-critic (graph method: soft actor-critic). 13 bricks; individually on a fixture: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 27 siblings

  1. SAC entry · level 0 · unverified · 4849ba61ae47dd70
  2. AlgorithmBase helper · level 0 · unverified · 110041979f3c0cb8
  3. Batch helper · level 1 · ran · 6bb425a4771dc88f
  4. ConcatStateAction helper · level 1 · ran · c10734f04f231cb4
  5. Logger helper · level 1 · ran · 4aec8353051fa16d
  6. MultiLinear helper · level 1 · ran · 5d3a98fbf8446e0c
  7. ReplayBuffer helper · level 1 · ran · e9664791458e5ade
  8. ScalarHolder helper · level 1 · ran · 33ec92b652664841
  9. SquashedDiagonalGaussianHead helper · level 1 · ran · 02a45597a277afab
  10. ortho_init helper · level 1 · ran · our draft was wrong · 5c5bce3523ed4d69
  11. polyak_update helper · level 0 · unverified · f299a2900b4034fa
  12. convert_to_tensor helper · level 1 · ran · our draft was wrong · cdf94e91c8746537
  13. group_by_keys helper · level 1 · ran · our draft was wrong · 1dd9b9ae9fa9426f

harvested Assembly for soft actor-critic (graph method: soft actor-critic). 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 27 siblings

  1. SAC_Trainer entry · level 0 · unverified · 3e1e70dd1d5f3958
  2. PolicyNetwork model · level 1 · ran · 540316788d2c30c7
  3. SoftQNetwork model · level 1 · ran · 0688d4da92feee38
  4. ReplayBuffer sampler · level 1 · ran · 70249df825c62d7e

harvested Assembly for soft actor-critic (graph method: soft actor-critic). 6 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 27 siblings

  1. mlp_actor_critic entry · level 0 · unverified · 8498689f07030ac8
  2. apply_squashing_func helper · level 0 · unverified · 198be549ce9696ef
  3. mlp helper · level 0 · unverified · e68b07bcdded00fa
  4. mlp_gaussian_policy model · level 0 · unverified · a860fee8188a0218
  5. clip_but_pass_gradient helper · level 1 · ran · honoured contract · 4731ca1d377b8284
  6. gaussian_likelihood helper · level 1 · ran · honoured contract · 5c26c93931dce503

harvested Assembly for soft actor-critic (graph method: soft actor-critic). 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 27 siblings

  1. SACActor entry · level 1 · ran · e5d43066162708ff
  2. RLNetwork helper · level 0 · unverified · b36d35fd411b0150

harvested Assembly for soft actor-critic (graph method: soft actor-critic). 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.

one of 27 siblings

  1. MLPActorCritic entry · level 1 · ran · a830c8ece63f9c57
  2. MLPGaussianPolicy model · level 1 · ran · c02fc6e11c3ba5cf
  3. MLPQFunction model · level 1 · ran · 14211bf5685457cf
  4. mlp helper · level 1 · ran · our draft was wrong · a1e9dc4773ffeba5

harvested Assembly for soft actor-critic (graph method: soft actor-critic). 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.

one of 27 siblings

  1. SoftActor entry · level 1 · ran · b473c449b3da39cc
  2. _create_fcnn model · level 1 · ran · our draft was wrong · b7fc01f37cbb0eb1

harvested Assembly for soft actor-critic (graph method: soft actor-critic). 13 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) · 9 unverified. The assembly has not been run end-to-end.

one of 27 siblings

  1. SAC entry · level 0 · unverified · 348b1924f106de50
  2. Algorithm helper · level 0 · unverified · eaf547baf5f33e43
  3. GaussianPolicy model · level 1 · ran · 8761dc745b44dc04
  4. TwinnedStateActionFunction model · level 1 · ran · 5d13132d2e3c5ef0
  5. assert_action helper · level 0 · unverified · ded76544fe9d6607
  6. disable_gradients helper · level 0 · unverified · 56dd8863f4522252
  7. soft_update helper · level 0 · unverified · e8abbe917721f0c8
  8. update_params helper · level 0 · unverified · 33523284389291bf
  9. BaseNetwork helper · level 0 · unverified · d6d4b5a5d84ba8ad
  10. create_linear_network helper · level 1 · ran; the contract check could not run (RAISES) · 248f63c9cf4d972e
  11. StateActionFunction model · level 1 · ran · b1e066bc1ff4b61b
  12. _soft_update helper · level 0 · unverified · 231f633be51bd617
  13. initialize_weights_xavier helper · level 0 · unverified · 544fe1f08a36cc62
  1. SAC · 6d1ab8e8bdfceece · 3 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) · 2 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. SAC · 71e70b31947abb15 · 8 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) · 4 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[13] in the JSON twin
  3. Agent · 7afa0732a741d65f · 12 bricks; individually on a fixture: 7 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; 3 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. SAC · 8aeea19ed7035e4d · 6 bricks; individually on a fixture: 5 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; 2 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
  5. SACLearner · 8ef2b775d0263949 · 4 bricks; individually on a fixture: 0 ran · 4 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
  6. SAC · 8f0e5a2033e2561b · 8 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) · 4 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[17] in the JSON twin
  7. SAC · 9adf4f562cd31d82 · 8 bricks; individually on a fixture: 4 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; 0 where Syntology's instrument failed) · 4 unverified · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
  8. SAC · ab52e9144e49f38b · 13 bricks; individually on a fixture: 9 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified · The assembly has not been run end-to-end · assemblies[19] in the JSON twin
  9. SAC · b9bb35d3946b1c03 · 7 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) · 4 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[20] in the JSON twin
  10. TanhGaussianPolicySACAdapt · bdd0e01576c7006a · 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[21] in the JSON twin
  11. SoftActorCritic · d403ed8fc6e6a467 · 7 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) · 5 unverified · The assembly has not been run end-to-end · assemblies[22] in the JSON twin
  12. SAC · d8d052895ed6eaaa · 11 bricks; individually on a fixture: 6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[23] in the JSON twin
  13. SAC · ea1ea881ec00edf6 · 7 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) · 4 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[24] in the JSON twin
  14. ReplayBuffer · f9d74563daee1fbd · 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[25] in the JSON twin
  15. policyNet · fe2e45dc0661c714 · 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[26] 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="1801.01290") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Continuous ControlDecision MakingDeep Reinforcement LearningOmniverse Isaac GymOpenAI GymQ-LearningReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Continuous Control Lunar Lander (OpenAI Gym) SAC Score 284.59±0.97 #1 of 5 Archive leaderboard report
OpenAI Gym Ant-v4 SAC Average Return 5208.09 #3 of 5 Archive leaderboard report
OpenAI Gym HalfCheetah-v4 SAC Average Return 15836.04 #1 of 5 Archive leaderboard report
OpenAI Gym Hopper-v4 SAC Average Return 2882.56 #3 of 5 Archive leaderboard report
OpenAI Gym Humanoid-v4 SAC Average Return 6211.50 #2 of 5 Archive leaderboard report
OpenAI Gym Walker2d-v4 SAC Average Return 5745.27 #1 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: Soft Actor Critic

AdamDense ConnectionsExperience ReplayReLUSoft Actor Critic

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