Papers › Benchmarking Deep Reinforcement Learning for Continuous Control

Benchmarking Deep Reinforcement Learning for Continuous Control

22 Apr 2016arXiv:1604.06778archive 2025-07-28

Yan Duan, Xi Chen, Rein Houthooft, John Schulman, Pieter Abbeel

Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning. Some notable examples include training agents to play Atari games based on raw pixel data and to acquire advanced manipulation skills using raw sensory inputs. However, it has been difficult to quantify progress in the domain of continuous control due to the lack of a commonly adopted benchmark. In this work, we present a benchmark suite of continuous control tasks, including classic tasks like cart-pole swing-up, tasks with very high state and action dimensionality such as 3D humanoid locomotion, tasks with partial observations, and tasks with hierarchical structure. We report novel findings based on the systematic evaluation of a range of implemented reinforcement learning algorithms. Both the benchmark and reference implementations are released at https://github.com/rllab/rllab in order to facilitate experimental reproducibility and to encourage adoption by other researchers.

PaperPDFCodeCode 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

The archive's official repository (rllab/rllab) was not harvested; the 4 samples below come from 1 community repository.

Syntology 4 code samples harvested from 1 repository linked to this paper: 3 ran (of which 0 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 4 samples from 1 repository, 3 ran (3 with no instrument failure; 0 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.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

rllab/rllab officialmentioned in papermentioned on GitHubtfNOASSERTIONSyntology: not harvested report
Dam930/rllab mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
bstadie/third_person_im mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
cathywu/rllab-multiagent mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
cbfinn/maml_rl mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
jachiam/cpo mentioned on GitHubSyntology: not harvested report
openai/rllab mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
rejuvyesh/rllab mentioned on GitHubNOASSERTIONSyntology: not harvested report
richardrl/cartpole-request-for-research mentioned on GitHubpytorchSyntology: not harvested report
rll/rllab mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
rlworkgroup/garage mentioned on GitHubtfMITSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
russellmendonca/maesn_suite mentioned on GitHubtfSyntology: not harvested report
sisl/event-driven-rllab mentioned on GitHubtfSyntology: not harvested report
sisl/gail-driver mentioned on GitHubNOASSERTIONSyntology: not harvested report
wyndwarrior/imitation_from_observation mentioned on GitHubtfSyntology: 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.

Code Syntology ran Syntology

4 samples harvested: 3 ran (of which 0 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. “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
1unverified

Licence: 0 of the 4 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 rlworkgroup/garage. “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.

rlworkgroup/garage community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
find_task_for_env_id_in_any_benchmark in 6 papers benchmarks/src/garage_benchmarks/benchmarks.py ran fingerprinted MIT (permissive) · 286b82196c4fe36b · report fixture: signature env_id:str/0/str · returned tuple · level recorded 2026-09-25
get_task in 28 papers benchmarks/src/garage_benchmarks/benchmarks.py ran MIT (permissive) · 8574703c48d0d43d · report fixture: signature benchmark:dict/0/?, env_id:str/0/str · returned dict · level recorded 2026-09-25
make_optimizer in 32 papers src/garage/_functions.py ran MIT (permissive) · 8a3741971be6face · report fixture: signature optimizer_type:callable/0/?, module:callable/0/?, lr:float/0/float, betas:tuple/1/float, eps:float/0/float, weight_decay:float/0/float · returned Adam · level recorded 2026-09-25
get_benchmark in 9 papers benchmarks/src/garage_benchmarks/benchmarks.py unverified MIT (permissive) · 4edad3b8d64c574e · report

Tasks

Action Triplet RecognitionAtari GamesBenchmarkingContinuous ControlDeep Reinforcement LearningReinforcement LearningReinforcement Learning (RL)continuous-controlreinforcement-learning

Datasets

Introduced by this paper, per the archive.

RLLab Framework

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Continuous Control 2D Walker TRPO Score 1353.8 #1 of 1 Archive leaderboard report
Continuous Control Acrobot TRPO Score -326 #1 of 1 Archive leaderboard report
Continuous Control Acrobot (limited sensors) TRPO Score -83.3 #1 of 1 Archive leaderboard report
Continuous Control Acrobot (noisy observations) TRPO Score -149.6 #1 of 1 Archive leaderboard report
Continuous Control Acrobot (system identifications) TRPO Score -170.9 #1 of 1 Archive leaderboard report
Continuous Control Ant TRPO Score 730.2 #1 of 1 Archive leaderboard report
Continuous Control Ant + Gathering TRPO Score -0.4 #1 of 1 Archive leaderboard report
Continuous Control Ant + Maze TRPO Score 0 #1 of 1 Archive leaderboard report
Continuous Control Cart-Pole Balancing TRPO Score 4869.8 #1 of 1 Archive leaderboard report
Continuous Control Cart-Pole Balancing (limited sensors) TRPO Score 960.2 #1 of 1 Archive leaderboard report
Continuous Control Cart-Pole Balancing (noisy observations) TRPO Score 606.2 #1 of 1 Archive leaderboard report
Continuous Control Cart-Pole Balancing (system identifications) TRPO Score 980.3 #1 of 1 Archive leaderboard report
Continuous Control Double Inverted Pendulum TRPO Score 4412.4 #1 of 1 Archive leaderboard report
Continuous Control Full Humanoid TRPO Score 287 #1 of 1 Archive leaderboard report
Continuous Control Half-Cheetah TRPO Score 1914 #1 of 1 Archive leaderboard report
Continuous Control Hopper TRPO Score 1183.3 #1 of 1 Archive leaderboard report
Continuous Control Inverted Pendulum TRPO Score 247.2 #1 of 1 Archive leaderboard report
Continuous Control Inverted Pendulum (limited sensors) TRPO Score 4.5 #1 of 1 Archive leaderboard report
Continuous Control Inverted Pendulum (noisy observations) TRPO Score 10.4 #1 of 1 Archive leaderboard report
Continuous Control Inverted Pendulum (system identifications) TRPO Score 14.1 #1 of 1 Archive leaderboard report
Continuous Control Mountain Car TRPO Score -61.7 #1 of 1 Archive leaderboard report
Continuous Control Mountain Car (limited sensors) TRPO Score -64.2 #1 of 1 Archive leaderboard report
Continuous Control Mountain Car (noisy observations) TRPO Score -60.2 #1 of 1 Archive leaderboard report
Continuous Control Mountain Car (system identifications) TRPO Score -61.6 #1 of 1 Archive leaderboard report
Continuous Control Simple Humanoid TRPO Score 269.7 #1 of 1 Archive leaderboard report
Continuous Control Swimmer TRPO Score 96 #1 of 1 Archive leaderboard report
Continuous Control Swimmer + Gathering TRPO Score 0 #1 of 1 Archive leaderboard report
Continuous Control Swimmer + Maze TRPO Score 0 #1 of 1 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.

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