Papers › Smooth Exploration for Robotic Reinforcement Learning

Smooth Exploration for Robotic Reinforcement Learning

12 May 2020arXiv:2005.05719archive 2025-07-28

Antonin Raffin, Jens Kober, Freek Stulp

Reinforcement learning (RL) enables robots to learn skills from interactions with the real world. In practice, the unstructured step-based exploration used in Deep RL -- often very successful in simulation -- leads to jerky motion patterns on real robots. Consequences of the resulting shaky behavior are poor exploration, or even damage to the robot. We address these issues by adapting state-dependent exploration (SDE) to current Deep RL algorithms. To enable this adaptation, we propose two extensions to the original SDE, using more general features and re-sampling the noise periodically, which leads to a new exploration method generalized state-dependent exploration (gSDE). We evaluate gSDE both in simulation, on PyBullet continuous control tasks, and directly on three different real robots: a tendon-driven elastic robot, a quadruped and an RC car. The noise sampling interval of gSDE permits to have a compromise between performance and smoothness, which allows training directly on the real robots without loss of performance. The code is available at https://github.com/DLR-RM/stable-baselines3.

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

No sample from the archive's official repository (DLR-RM/stable-baselines3) is linked to this paper; the 1 sample below comes from 1 community repository. Syntology harvested code from DLR-RM/stable-baselines3 for another paper.

DLR-RM/stable-baselines3: 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.

Syntology 1 code sample harvested from 1 repository linked to this paper: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 1 sample from 1 repository, 1 ran (1 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.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

DLR-RM/stable-baselines3 officialmentioned in paperpytorchSyntology: 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
markub3327/rl-toolkit mentioned on GitHubtfMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
araffin/sbx jaxSyntology: 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
facebookresearch/rl jaxMITSyntology: 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

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

1 sample harvested: 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. “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.

1ran

Licence: 0 of the 1 sample 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 markub3327/rl-toolkit. “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.

markub3327/rl-toolkit 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

Tasks

Continuous ControlReinforcement LearningReinforcement Learning (RL)continuous-controlreinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Continuous Control PyBullet Ant SAC gSDE Return 3459 #1 of 8 Archive leaderboard report
Continuous Control PyBullet Ant TD3 gSDE Return 3267 #2 of 8 Archive leaderboard report
Continuous Control PyBullet Ant TD3 Return 2865 #3 of 8 Archive leaderboard report
Continuous Control PyBullet Ant SAC Return 2859 #4 of 8 Archive leaderboard report
Continuous Control PyBullet Ant PPO gSDE Return 2587 #5 of 8 Archive leaderboard report
Continuous Control PyBullet Ant A2C gSDE Return 2560 #6 of 8 Archive leaderboard report
Continuous Control PyBullet Ant PPO Return 2160 #7 of 8 Archive leaderboard report
Continuous Control PyBullet Ant A2C Return 1967 #8 of 8 Archive leaderboard report
Continuous Control PyBullet HalfCheetah SAC Return 2883 #1 of 8 Archive leaderboard report
Continuous Control PyBullet HalfCheetah SAC gSDE Return 2850 #2 of 8 Archive leaderboard report
Continuous Control PyBullet HalfCheetah PPO + gSDE Return 2760 #3 of 8 Archive leaderboard report
Continuous Control PyBullet HalfCheetah TD3 Return 2687 #4 of 8 Archive leaderboard report
Continuous Control PyBullet HalfCheetah TD3 gSDE Return 2578 #5 of 8 Archive leaderboard report
Continuous Control PyBullet HalfCheetah PPO Return 2254 #6 of 8 Archive leaderboard report
Continuous Control PyBullet HalfCheetah A2C + gSDE Return 2028 #7 of 8 Archive leaderboard report
Continuous Control PyBullet HalfCheetah A2C Return 1652 #8 of 8 Archive leaderboard report
Continuous Control PyBullet Hopper SAC gSDE Return 2646 #1 of 8 Archive leaderboard report
Continuous Control PyBullet Hopper PPO gSDE Return 2508 #2 of 8 Archive leaderboard report
Continuous Control PyBullet Hopper SAC Return 2477 #3 of 8 Archive leaderboard report
Continuous Control PyBullet Hopper TD3 Return 2470 #4 of 8 Archive leaderboard report
Continuous Control PyBullet Hopper TD3 gSDE Return 2353 #5 of 8 Archive leaderboard report
Continuous Control PyBullet Hopper PPO Return 1622 #6 of 8 Archive leaderboard report
Continuous Control PyBullet Hopper A2C Return 1559 #7 of 8 Archive leaderboard report
Continuous Control PyBullet Hopper A2C gSDE Return 1448 #8 of 8 Archive leaderboard report
Continuous Control PyBullet Walker2D SAC gSDE Return 2341 #1 of 8 Archive leaderboard report
Continuous Control PyBullet Walker2D SAC Return 2215 #2 of 8 Archive leaderboard report
Continuous Control PyBullet Walker2D TD3 Return 2106 #3 of 8 Archive leaderboard report
Continuous Control PyBullet Walker2D TD3 gSDE Return 1989 #4 of 8 Archive leaderboard report
Continuous Control PyBullet Walker2D PPO gSDE Return 1776 #5 of 8 Archive leaderboard report
Continuous Control PyBullet Walker2D PPO Return 1238 #6 of 8 Archive leaderboard report
Continuous Control PyBullet Walker2D A2C gSDE Return 694 #7 of 8 Archive leaderboard report
Continuous Control PyBullet Walker2D A2C Return 443 #8 of 8 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: gSDE

A2CAdamClipped Double Q-learningDense ConnectionsEntropy RegularizationExperience ReplayPPOReLUSoft Actor CriticTD3Target Policy SmoothinggSDE

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