Papers › Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation

Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation

17 Jul 2023NeurIPS 2023 11arXiv:2307.08875archive 2025-07-28

Ruida Zhou, Tao Liu, Min Cheng, Dileep Kalathil, P. R. Kumar, Chao Tian

We study robust reinforcement learning (RL) with the goal of determining a well-performing policy that is robust against model mismatch between the training simulator and the testing environment. Previous policy-based robust RL algorithms mainly focus on the tabular setting under uncertainty sets that facilitate robust policy evaluation, but are no longer tractable when the number of states scales up. To this end, we propose two novel uncertainty set formulations, one based on double sampling and the other on an integral probability metric. Both make large-scale robust RL tractable even when one only has access to a simulator. We propose a robust natural actor-critic (RNAC) approach that incorporates the new uncertainty sets and employs function approximation. We provide finite-time convergence guarantees for the proposed RNAC algorithm to the optimal robust policy within the function approximation error. Finally, we demonstrate the robust performance of the policy learned by our proposed RNAC approach in multiple MuJoCo environments and a real-world TurtleBot navigation task.

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

Syntology 14 code samples harvested from 1 repository linked to this paper: 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. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 11 ran (9 with no instrument failure; 2 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 11 samples that ran have no recorded date.

tliu1997/rnac officialmentioned in papermentioned on GitHubpytorchSyntology: 14 samples, 11 ran (2 instrument-failed) · 3 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested: 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. “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 · honoured contract
2ran · our draft was wrong
8ran
3unverified

Licence: 14 of the 14 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 tliu1997/rnac. “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 4 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.

tliu1997/rnac official repository 14 samples, 11 ran (2 instrument-failed) · 3 unverified
Actor_Beta train_rnac.py ran fingerprinted no licence file found · pointer only · ae933dfddf8823fa · report fixture: returned Actor_Beta · level recorded 2026-09-22
Actor_Gaussian train_rnac.py ran fingerprinted no licence file found · pointer only · b7e663349c62bb98 · report fixture: returned Actor_Gaussian · level recorded 2026-09-22
Critic in 60 papers train_rnac.py ran fingerprinted no licence file found · pointer only · 40af160a65b521e5 · report fixture: returned Critic · level recorded 2026-09-22
Normalization in 11 papers train_rnac.py ran no licence file found · pointer only · 609d32bfa5631924 · report fixture: returned Normalization · level recorded 2026-09-22
PPO_continuous train_rnac.py ran no licence file found · pointer only · fe09cbc7d1ab50c5 · report fixture: returned PPO_continuous · level recorded 2026-09-22
ReplayBuffer in 33 papers train_rnac.py ran no licence file found · pointer only · 31b7a842f737b97e · report fixture: returned ReplayBuffer · level recorded 2026-09-22
RewardScaling train_rnac.py ran fingerprinted no licence file found · pointer only · e7306d3fb1ac4b07 · report fixture: returned RewardScaling · level recorded 2026-09-22
RunningMeanStd in 13 papers train_rnac.py ran no licence file found · pointer only · 8b5734917fdb6af3 · report fixture: returned RunningMeanStd · level recorded 2026-09-22
evaluate_policy in 12 papers train_rnac.py ran · honoured contract no licence file found · pointer only · f74e37440bbe7726 · report fixture: signature args:Args/0/?, env:SimpleEnv/0/?, agent:callable/0/?, state_norm:callable/0/? · returned float · level recorded, date not recorded
evaluate_policy in 12 papers eval_rnac.py ran · our draft was wrong no licence file found · pointer only · b49898d9bdfeb500 · report fixture: signature args:Args/0/?, env:MockEnv/0/?, agent:callable/0/?, state_norm:callable/0/?, springref:float/0/float, x:ndarray/1/float · returned float · level recorded, date not recorded
load_agent eval_rnac.py ran · our draft was wrong no licence file found · pointer only · 47b736f56e823740 · report fixture: signature agent:MinimalAgent/0/?, load_path:str/0/str, device:device/0/? · returned tuple · level recorded, date not recorded
main in 235 papers train_rnac.py unverified no licence file found · pointer only · 787f96a4f64c5b9d · report
orthogonal_init in 12 papers train_rnac.py unverified no licence file found · pointer only · aaec1511480533d6 · report
save_agent train_rnac.py unverified no licence file found · pointer only · 0b2b2d21541f3b92 · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Robust Natural Actor-Critic (RNAC) (graph method: Robust Natural Actor-Critic (RNAC)). 12 bricks; individually on a fixture: 9 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; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. main entry · level 0 · unverified · 787f96a4f64c5b9d
  2. Normalization data_transform · level 1 · ran · 609d32bfa5631924
  3. PPO_continuous helper · level 1 · ran · fe09cbc7d1ab50c5
  4. ReplayBuffer sampler · level 1 · ran · 31b7a842f737b97e
  5. RewardScaling data_transform · level 1 · ran · e7306d3fb1ac4b07
  6. evaluate_policy metric · level 1 · ran · honoured contract · f74e37440bbe7726
  7. save_agent helper · level 0 · unverified · 0b2b2d21541f3b92
  8. RunningMeanStd helper · level 1 · ran · 8b5734917fdb6af3
  9. Actor_Beta helper · level 1 · ran · ae933dfddf8823fa
  10. Actor_Gaussian helper · level 1 · ran · b7e663349c62bb98
  11. Critic helper · level 1 · ran · 40af160a65b521e5
  12. orthogonal_init helper · level 0 · unverified · aaec1511480533d6

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="2307.08875") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

MuJoCoReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

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