Papers › PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning

PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning

16 Jul 2020NeurIPS 2020 12arXiv:2007.08459archive 2025-07-28

Alekh Agarwal, Mikael Henaff, Sham Kakade, Wen Sun

Direct policy gradient methods for reinforcement learning are a successful approach for a variety of reasons: they are model free, they directly optimize the performance metric of interest, and they allow for richly parameterized policies. Their primary drawback is that, by being local in nature, they fail to adequately explore the environment. In contrast, while model-based approaches and Q-learning directly handle exploration through the use of optimism, their ability to handle model misspecification and function approximation is far less evident. This work introduces the the Policy Cover-Policy Gradient (PC-PG) algorithm, which provably balances the exploration vs. exploitation tradeoff using an ensemble of learned policies (the policy cover). PC-PG enjoys polynomial sample complexity and run time for both tabular MDPs and, more generally, linear MDPs in an infinite dimensional RKHS. Furthermore, PC-PG also has strong guarantees under model misspecification that go beyond the standard worst case ℓ_∞ assumptions; this includes approximation guarantees for state aggregation under an average case error assumption, along with guarantees under a more general assumption where the approximation error under distribution shift is controlled. We complement the theory with empirical evaluation across a variety of domains in both reward-free and reward-driven settings.

PaperPDFConference PDFCodeCode 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="2007.08459")

Code

Syntology Ran 3 of 9 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 1 ran with no contract checked.

By repository: community (archive-listed): 8 samples from 1 repository, 2 ran; 1 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.

mbhenaff/pcpg mentioned on GitHubtfMIT 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

9 samples harvested; 3 ran; 1 honoured the contract we drafted; 6 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.

1ran · honoured contract
1ran · our draft was wrong
1ran
6unverified

Licence: 1 of the 9 samples is 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 mbhenaff/pcpg. 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.

make_output_format mbhenaff/pcpg/baselines/logger.py community (archive-listed) ran MIT (permissive) · bcd8b4acab199405 · report
register mbhenaff/pcpg/baselines/common/models.py community (archive-listed) ran · our draft was wrong MIT (permissive) · a44574392d168384 · report
build_impala_cnn mbhenaff/pcpg/baselines/common/models.py community (archive-listed) unverified MIT (permissive) · 2bf5c781f8e4aad5 · report
profile mbhenaff/pcpg/baselines/logger.py community (archive-listed) unverified MIT (permissive) · 91a934c3d796a9d4 · report
read_json mbhenaff/pcpg/baselines/logger.py community (archive-listed) unverified MIT (permissive) · 88ef5a17fc986d9a · report
rolling_window mbhenaff/pcpg/baselines/results_plotter.py community (archive-listed) unverified MIT (permissive) · 895ca4b776fb6d6d · report
ts2xy mbhenaff/pcpg/baselines/results_plotter.py community (archive-listed) unverified MIT (permissive) · 4ab4ad5ff9820e39 · report
window_func mbhenaff/pcpg/baselines/results_plotter.py community (archive-listed) unverified MIT (permissive) · 43741b9339bd80da · report
flatten_lists identical code first harvested elsewhere ran · honoured contract licence of this copy not recorded · 0173e4280d9a9884 · report

Tasks

Policy Gradient MethodsQ-Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Q-Learning

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