SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.08560 · ICLR · 2024

Dual RL: Unification and New Methods for Reinforcement and Imitation Learning

Scott Niekum, Amy Zhang, Qinqing Zheng, Harshit Sikchi

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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; 0 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 2 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/2302.08560.json · badge: /api/ran/2302.08560.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
hari-sikchi/DVL marked official in Papers with Code
Papers with Code archive
4 ran · 1 no recorded run
FunctionStatusWhere it lives
chi_square_loss Ran
ran, violated the contract we drafted
hari-sikchi/DVL/offline/critic.py
pointer only (licence: NONE) · get_code("143f39ac7129288e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hari-sikchi/DVL 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.

reverse_kl_loss Ran
ran; our contract draft was wrong, not the code
hari-sikchi/DVL/offline/critic.py
pointer only (licence: NONE) · get_code("53d821721fbb5fe1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hari-sikchi/DVL 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.

total_variation_loss Ran
ran, violated the contract we drafted
hari-sikchi/DVL/offline/critic.py
pointer only (licence: NONE) · get_code("d773884e980e01c5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hari-sikchi/DVL 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.

update_v Ran
ran; our contract draft was wrong, not the code
hari-sikchi/DVL/offline/critic.py
pointer only (licence: NONE) · get_code("d3aa5cd1dcb8eff9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hari-sikchi/DVL 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.

Model Not yet run
unverified (harvested, no recorded run)
hari-sikchi/DVL/offline/critic.py
pointer only (licence: NONE) · get_code("ac1979a869131b2d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hari-sikchi/DVL 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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
Model
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2210.04251 (2022-10)
State Advantage Weighting for Offline RL

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

The goal of reinforcement learning (RL) is to find a policy that maximizes the expected cumulative return. It has been shown that this objective can be represented as an optimization problem of state-action visitation distribution under linear constraints. The dual problem of this formulation, which we refer to as dual RL, is unconstrained and easier to optimize. In this work, we first cast several state-of-the-art offline RL and offline imitation learning (IL) algorithms as instances of dual RL approaches with shared structures. Such unification allows us to identify the root cause of the shortcomings of prior methods. For offline IL, our analysis shows that prior methods are based on a restrictive coverage assumption that greatly limits their performance in practice. To fix this limitation, we propose a new discriminator-free method ReCOIL that learns to imitate from arbitrary off-policy data to obtain near-expert performance. For offline RL, our analysis frames a recent offline RL method XQL in the dual framework, and we further propose a new method f -DVL that provides alternative choices to the Gumbel regression loss that fixes the known training instability issue of XQL. The performance improvements by both of our proposed methods, ReCOIL and f -DVL, in IL and RL are validated on an extensive suite of simulated robot locomotion and manipulation tasks.

For agents

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

get_harvested_code_for_paper("2302.08560")
get_code_for_paper("2302.08560")
have("2302.08560")

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

curl https://syntology.ai/api/ran/2302.08560.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.08560.svg)](https://syntology.ai/paper/2302.08560)

Connect an agent — have() is free.