SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.08459 · 2020

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

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 2 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2007.08459.json · badge: /api/ran/2007.08459.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
mbhenaff/pcpg community (classifier label)
classifier basis not recorded on the link
5 ran · 3 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
flatten_lists Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from Jekyll1021/RARL
pointer only; the stored copy get_code serves, from Jekyll1021/RARL, is pointer only (licence: NONE) · get_code("0173e4280d9a9884")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_output_format Ran
ran; our contract draft was wrong, not the code
mbhenaff/pcpg/baselines/logger.py
code served (permissive licence) · get_code("bcd8b4acab199405")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned HumanOutputFormat. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import sys
import tempfile

# Create a temporary directory for output
temp_dir = tempfile.mkdtemp()

ARGS = {
    'format': 'log',
    'ev_dir': temp_dir,
    'log_suffix': '_test'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type HumanOutputFormat — a HumanOutputFormat output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a HumanOutputFormat output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
register Ran
ran; our contract draft was wrong, not the code
mbhenaff/pcpg/baselines/common/models.py
code served (permissive licence) · get_code("a44574392d168384")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

# The register function is a decorator factory that takes a name parameter
# and returns a decorator that registers functions in a mapping dict.
# We just need to provide a string name.

ARGS = {
    "name": "my_function"
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
rolling_window Ran
ran on a synthesized input
mbhenaff/pcpg/baselines/results_plotter.py
pointer only (licence: MIT); the stored copy get_code serves, from knowledgetechnologyuhh/goal_conditioned_RL_baselines, is pointer only (licence: MIT) · get_code("895ca4b776fb6d6d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from knowledgetechnologyuhh/goal_conditioned_RL_baselines, and MIT, as GitHub detects it on that repository, is in the permissive set, but a licence decision keeps the body a pointer: its licence file names an outside party, so it may cover vendored code rather than the repository owner's files (recorded as pointer:licence_names_third_party_corporation). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ts2xy Ran
ran on a synthesized input
mbhenaff/pcpg/baselines/results_plotter.py
pointer only (licence: MIT); the stored copy get_code serves, from knowledgetechnologyuhh/goal_conditioned_RL_baselines, is pointer only (licence: MIT) · get_code("4ab4ad5ff9820e39")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from knowledgetechnologyuhh/goal_conditioned_RL_baselines, and MIT, as GitHub detects it on that repository, is in the permissive set, but a licence decision keeps the body a pointer: its licence file names an outside party, so it may cover vendored code rather than the repository owner's files (recorded as pointer:licence_names_third_party_corporation). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

window_func Ran
ran on a synthesized input
mbhenaff/pcpg/baselines/results_plotter.py
pointer only (licence: MIT); the stored copy get_code serves, from knowledgetechnologyuhh/goal_conditioned_RL_baselines, is pointer only (licence: MIT) · get_code("43741b9339bd80da")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from knowledgetechnologyuhh/goal_conditioned_RL_baselines, and MIT, as GitHub detects it on that repository, is in the permissive set, but a licence decision keeps the body a pointer: its licence file names an outside party, so it may cover vendored code rather than the repository owner's files (recorded as pointer:licence_names_third_party_corporation). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

build_impala_cnn Not yet run
unverified (harvested, no recorded run)
mbhenaff/pcpg/baselines/common/models.py
pointer only (licence: MIT); the stored copy get_code serves, from linzichuan/sdpo, is pointer only (licence: MIT) · get_code("2bf5c781f8e4aad5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from linzichuan/sdpo, and MIT, as GitHub detects it on that repository, is in the permissive set, but a licence decision keeps the body a pointer: its licence file names an outside party, so it may cover vendored code rather than the repository owner's files (recorded as pointer:licence_names_third_party_corporation). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

profile Not yet run
unverified (harvested, no recorded run)
mbhenaff/pcpg/baselines/logger.py
pointer only (licence: MIT); the stored copy get_code serves, from linzichuan/sdpo, is pointer only (licence: MIT) · get_code("91a934c3d796a9d4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from linzichuan/sdpo, and MIT, as GitHub detects it on that repository, is in the permissive set, but a licence decision keeps the body a pointer: its licence file names an outside party, so it may cover vendored code rather than the repository owner's files (recorded as pointer:licence_names_third_party_corporation). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

read_json Not yet run
unverified (harvested, no recorded run)
mbhenaff/pcpg/baselines/logger.py
code served (permissive licence) · get_code("88ef5a17fc986d9a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 0 the same month, 8 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
make_output_format 73 other papers
13 dated earlier, 60 later
1611.05763 (2016-11)
Learning to reinforcement learn
1804.06459 (2018-04)
On Learning Intrinsic Rewards for Policy Gradient Methods
1806.02473 (2018-06)
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
and 70 more not named here
profile 61 other papers
4 dated earlier, 57 later
1611.05763 (2016-11)
Learning to reinforcement learn
1905.06750 (2019-05)
Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation
1906.05841 (2019-06)
Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards
and 58 more not named here
read_json 22 other papers
14 dated earlier, 8 later
1611.05763 (2016-11)
Learning to reinforcement learn
1711.00123 (2017-11)
Backpropagation through the Void: Optimizing control variates for black-box gradient estimation
1804.06459 (2018-04)
On Learning Intrinsic Rewards for Policy Gradient Methods
and 19 more not named here
register 12 other papers
9 dated earlier, 3 later
1611.05763 (2016-11)
Learning to reinforcement learn
1708.05144 (2017-08)
Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
1905.02363 (2019-05)
Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning
and 9 more not named here
rolling_window 12 other papers
10 dated earlier, 2 later
1611.05763 (2016-11)
Learning to reinforcement learn
1804.06459 (2018-04)
On Learning Intrinsic Rewards for Policy Gradient Methods
1806.02473 (2018-06)
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
and 9 more not named here
window_func 10 other papers
9 dated earlier, 1 later
1611.05763 (2016-11)
Learning to reinforcement learn
1804.06459 (2018-04)
On Learning Intrinsic Rewards for Policy Gradient Methods
1806.02473 (2018-06)
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
and 7 more not named here
flatten_lists 8 other papers
6 dated earlier, 2 later
1606.03476 (2016-06)
Generative Adversarial Imitation Learning
1703.02702 (2017-03)
Robust Adversarial Reinforcement Learning
1801.01432 (2018-01)
Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning
and 5 more not named here
ts2xy 5 other papers
5 dated earlier
1611.05763 (2016-11)
Learning to reinforcement learn
1905.04100 (2019-05)
Deep Reinforcement Learning using Genetic Algorithm for Parameter Optimization
1905.06750 (2019-05)
Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation
and 2 more not named here
build_impala_cnn 2 other papers
1 dated earlier, 1 later
1906.05841 (2019-06)
Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards
2302.02299 (2023-02)
Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 $\ell_{\infty}$ 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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2007.08459")
get_code_for_paper("2007.08459")
have("2007.08459")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2007.08459.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2007.08459.svg)](https://syntology.ai/paper/2007.08459)

Connect an agent — have() is free.