Papers › Trust Region Policy Optimization

Trust Region Policy Optimization

19 Feb 2015arXiv:1502.05477archive 2025-07-28

John Schulman, Sergey Levine, Philipp Moritz, Michael. I. Jordan, Pieter Abbeel

We describe an iterative procedure for optimizing policies, with guaranteed monotonic improvement. By making several approximations to the theoretically-justified procedure, we develop a practical algorithm, called Trust Region Policy Optimization (TRPO). This algorithm is similar to natural policy gradient methods and is effective for optimizing large nonlinear policies such as neural networks. Our experiments demonstrate its robust performance on a wide variety of tasks: learning simulated robotic swimming, hopping, and walking gaits; and playing Atari games using images of the screen as input. Despite its approximations that deviate from the theory, TRPO tends to give monotonic improvement, with little tuning of hyperparameters.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1502.05477")

Code

Syntology Ran 7 of 17 code samples harvested from 7 repositories linked to this paper; 10 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: community (archive-listed): 15 samples from 7 repositories, 6 ran; 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

Khrylx/PyTorch-RL mentioned on GitHubpytorch report
ailab-pku/rl-framework mentioned on GitHubpytorch report
chainer/chainerrl mentioned on GitHubpytorch report
ifestus/rl mentioned on GitHubtf report
ikostrikov/pytorch-rl mentioned on GitHubpytorch report
ikostrikov/pytorch-trpo mentioned on GitHubpytorch report
magnusja/ppo mentioned on GitHubtf report
marload/DeepRL-TensorFlow2 mentioned on GitHubtf report
nitthilan/pommerman mentioned on GitHub report
pat-coady/trpo mentioned on GitHubtf report
sirdr/TRPO.jl mentioned on GitHub report
tensorlayer/RLzoo mentioned on GitHubtf report
MindSpore-scientific/code-2 mindsporeApache-2.0 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

17 samples harvested; 7 ran; 2 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
1ran · fixture could not drive it
4ran
10unverified

Licence: 7 of the 17 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 7 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

KLEntropy pat-coady/trpo/trpo/policy.py community (archive-listed) ran MIT (permissive) · 21087806cd98f0eb · report
LogProb pat-coady/trpo/trpo/policy.py community (archive-listed) ran MIT (permissive) · cb1881154c084926 · report
PolicyNN pat-coady/trpo/trpo/policy.py community (archive-listed) ran MIT (permissive) · adb1b2f8460af76c · report
TRPOAgent ifestus/rl/policy_agents.py community (archive-listed) ran no licence file found · pointer only · 68f53fd02ecf2c67 · report
flatgrad spideralessio/TRPO-Tensorflow2/TRPO.py community (archive-listed) ran · honoured contract no licence file found · pointer only · 624753be66ae25df · report
flatvars spideralessio/TRPO-Tensorflow2/TRPO.py community (archive-listed) ran · honoured contract no licence file found · pointer only · 7c5c823b328af93a · report
Policy magnusja/ppo/src/policy.py community (archive-listed) unverified MIT (permissive) · b11d0213b416df62 · report
TRPO spideralessio/TRPO-Tensorflow2/TRPO.py community (archive-listed) unverified no licence file found · pointer only · bc789c354e38ee20 · report
TRPO pat-coady/trpo/trpo/policy.py community (archive-listed) unverified MIT (permissive) · f51bd581b9a86ab1 · report
TRPO tensorlayer/RLzoo/rlzoo/algorithms/trpo/trpo.py community (archive-listed) unverified Apache-2.0 (permissive) · 84ac3feb93cdf5c7 · report
assign_vars spideralessio/TRPO-Tensorflow2/TRPO.py community (archive-listed) unverified no licence file found · pointer only · 16b584c62bee3a78 · report
conjugate_gradients Khrylx/PyTorch-RL/core/trpo.py community (archive-listed) unverified MIT (permissive) · 8946170b041be61b · report
linesearch ikostrikov/pytorch-trpo/trpo.py community (archive-listed) unverified MIT (permissive) · 6b18e6942fb60f72 · report
trpo_step ikostrikov/pytorch-trpo/trpo.py community (archive-listed) unverified MIT (permissive) · 6bcf14c615d2dc3a · report
trpo_step Khrylx/PyTorch-RL/core/trpo.py community (archive-listed) unverified MIT (permissive) · 52129aa1d9bff078 · report
conjugate_gradients identical code first harvested elsewhere ran · fixture could not drive it licence of this copy not recorded · 918891131c62a121 · report
line_search identical code first harvested elsewhere unverified licence of this copy not recorded · f7c68d288ffc351b · report

Tasks

Atari GamesPolicy Gradient Methods

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: TRPO

TRPO

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