SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.03141 · ICML · 2024

Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays

Chao Huang, J Ürgen Schmidhuber, Qi Zhu, Yuhui Wang, Yixuan Wang, Simon Zhan, Qingyuan Wu, Chung-Wei Lin, Chen Lv

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 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; 4 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 5 failures of our instrument; 1 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/2402.03141.json · badge: /api/ran/2402.03141.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
QingyuanWuNothing/AD-RL canonical (classifier label)
classifier basis: census
10 ran · 0 no recorded run
qingyuanwunothing/ad-rl canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
action_value Ran
ran, honoured the contract we drafted
QingyuanWuNothing/AD-RL/DETERMINISTIC-MDP.py
pointer only (licence: NONE) · get_code("d27cd46bef9cd5a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QingyuanWuNothing/AD-RL when it was checked. 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.

find_specific_exp_tag Ran
ran, violated the contract we drafted
QingyuanWuNothing/AD-RL/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from QingyuanWuNothing/VDPO, is pointer only (licence: NONE) · get_code("8d481d190b83d758")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QingyuanWuNothing/AD-RL when it was checked. 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.

greedy_action Ran
ran, honoured the contract we drafted
QingyuanWuNothing/AD-RL/DETERMINISTIC-MDP.py
pointer only (licence: NONE) · get_code("4562c1fef99e80f7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QingyuanWuNothing/AD-RL when it was checked. 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.

layer_init Ran
ran; our contract draft was wrong, not the code
QingyuanWuNothing/AD-RL/nn.py
pointer only (licence: NONE); the stored copy get_code serves, from jaggbow/saf, is pointer only (licence: NONE) · get_code("beb42d440ccf2925")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QingyuanWuNothing/AD-RL when it was checked. 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_anneal_lr Ran
ran, honoured the contract we drafted
QingyuanWuNothing/AD-RL/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from QingyuanWuNothing/VDPO, is pointer only (licence: NONE) · get_code("c21517332c327b92")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QingyuanWuNothing/AD-RL when it was checked. 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_classical_env Ran
ran; our contract draft was wrong, not the code
QingyuanWuNothing/AD-RL/make_env.py
pointer only (licence: NONE) · get_code("7c5acb79755772b3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QingyuanWuNothing/AD-RL when it was checked. 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_classical_obs_delay_env Ran
ran; our contract draft was wrong, not the code
QingyuanWuNothing/AD-RL/make_env.py
pointer only (licence: NONE) · get_code("954a62d688488366")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QingyuanWuNothing/AD-RL when it was checked. 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_linear_schedule Ran
ran, honoured the contract we drafted
QingyuanWuNothing/AD-RL/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from QingyuanWuNothing/VDPO, is pointer only (licence: NONE) · get_code("bdf1781d7265fc58")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QingyuanWuNothing/AD-RL when it was checked. 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_vector_classical_envs Ran
ran; our contract draft was wrong, not the code
QingyuanWuNothing/AD-RL/make_env.py
pointer only (licence: NONE) · get_code("af3f16c8beef0513")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QingyuanWuNothing/AD-RL when it was checked. 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.

step Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
QingyuanWuNothing/AD-RL/DETERMINISTIC-MDP.py
pointer only (licence: NONE) · get_code("6abe638592f2fc98")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QingyuanWuNothing/AD-RL when it was checked. 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.

ReplayBuffer Not yet run
unverified (harvested, no recorded run)
qingyuanwunothing/ad-rl/AD-DQN.py
pointer only (licence: NONE) · get_code("68200fece3c9d915")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qingyuanwunothing/ad-rl when it was checked. 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.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 4 later) and 7 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
layer_init 28 other papers
14 dated earlier, 1 the same month, 10 later, 2 same year, order not determinable, 1 undated · 2 only as an assembly brick
1611.02779 (2016-11)
RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
1611.05763 (2016-11)
Learning to reinforcement learn
1703.03400 (2017-03)
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
and 25 more not named here
find_specific_exp_tag 1 other paper
1 later
2405.14226 (2024-05)
Variational Delayed Policy Optimization
make_anneal_lr 1 other paper
1 later
2405.14226 (2024-05)
Variational Delayed Policy Optimization
make_linear_schedule 1 other paper
1 later
2405.14226 (2024-05)
Variational Delayed 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

Reinforcement learning (RL) is challenging in the common case of delays between events and their sensory perceptions. State-of-the-art (SOTA) state augmentation techniques either suffer from state space explosion or performance degeneration in stochastic environments. To address these challenges, we present a novel Auxiliary-Delayed Reinforcement Learning (AD-RL) method that leverages auxiliary tasks involving short delays to accelerate RL with long delays, without compromising performance in stochastic environments. Specifically, AD-RL learns a value function for short delays and uses bootstrapping and policy improvement techniques to adjust it for long delays. We theoretically show that this can greatly reduce the sample complexity. On deterministic and stochastic benchmarks, our method significantly outperforms the SOTAs in both sample efficiency and policy performance. Code is available at https://github.com/QingyuanWuNothing/AD-RL.

For agents

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

get_harvested_code_for_paper("2402.03141")
get_code_for_paper("2402.03141")
have("2402.03141")

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

curl https://syntology.ai/api/ran/2402.03141.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.03141.svg)](https://syntology.ai/paper/2402.03141)

Connect an agent — have() is free.