SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.02328 · ICLR · 2023

Extreme Q-Learning: MaxEnt RL without Entropy

Stefano Ermon, Matthieu Geist, Divyansh Garg, Joey Hejna

arXiv · PDF · Open in the Atlas

Code that ran

8 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 3 failures of our instrument; 5 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/2301.02328.json · badge: /api/ran/2301.02328.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
zzmtsvv/rl_task community
Papers with Code archive
5 ran · 1 no recorded run
typoverflow/OfflineRL-Lib community
Papers with Code archive
1 ran · 4 no recorded run
div99/xql community
Papers with Code archive
1 ran · 0 no recorded run
xavierchanglingli/regularized-optimal-experience-replay community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Actor Ran
ran on a synthesized input · constructed an object; no result was computed
zzmtsvv/rl_task/eql/eql.py
pointer only (licence: NONE) · get_code("f7541cc0796ce882")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zzmtsvv/rl_task 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.

EnsembledCritic Ran
ran on a synthesized input · constructed an object; no result was computed
zzmtsvv/rl_task/eql/eql.py
pointer only (licence: NONE) · get_code("8f0d43f39f0d89d8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zzmtsvv/rl_task 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.

EnsembledLinear Ran
ran on a synthesized input · constructed an object; no result was computed
zzmtsvv/rl_task/eql/eql.py
pointer only (licence: NONE) · get_code("b3d4a42dc71fda39")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zzmtsvv/rl_task 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.

ValueFunction Ran
ran on a synthesized input · constructed an object; no result was computed
zzmtsvv/rl_task/eql/eql.py
pointer only (licence: NONE) · get_code("6788c15bff8f7d36")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zzmtsvv/rl_task 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.

eql_config Ran
ran on a synthesized input · constructed an object; no result was computed
zzmtsvv/rl_task/eql/eql.py
pointer only (licence: NONE) · get_code("d9d06fd7d266fb8d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zzmtsvv/rl_task 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.

gumbel_rescale_loss Ran
ran; our contract draft was wrong, not the code
div99/xql/offline/critic.py
pointer only (licence: NONE) · get_code("99acc42803f64ff1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, div99/xql 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.

gumbel_rescale_loss Ran
ran; our contract draft was wrong, not the code
xavierchanglingli/regularized-optimal-experience-replay/critic.py
code served (permissive licence) · get_code("181fe198b778da69")
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) and returned tuple. 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 jax
import jax.numpy as jnp

class Args:
    def __init__(self, gumbel_max_clip=None):
        self.gumbel_max_clip = gumbel_max_clip

# Create small test tensors
diff = jnp.array([[0.5, 1.2, -0.3, 0.8],
                   [0.1, -0.5, 0.9, 0.2]])

alpha = 0.5

args = Args(gumbel_max_clip=2.0)

ARGS = {
    "diff": diff,
    "alpha": alpha,
    "args": args
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
jax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
gumbel_rescale_loss Ran
ran; our contract draft was wrong, not the code
typoverflow/OfflineRL-Lib/offlinerllib/policy/model_free/xql.py
code served (permissive licence) · get_code("df90326c73fa9091")
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) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Create small tensors for pred and target
# The function performs element-wise operations, so shapes should match
batch_size = 2
dim_size = 4

pred = torch.randn(batch_size, dim_size)
target = torch.randn(batch_size, dim_size)

ARGS = {
    "pred": pred,
    "target": target,
    "alpha": 1.0,
    "clip_max": 7.0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
CategoricalActor Not yet run
unverified (harvested, no recorded run)
typoverflow/OfflineRL-Lib/offlinerllib/policy/model_free/xql.py
code served (permissive licence) · get_code("37d0a4a0d1f30a1c")
How it ran

no invocation recorded.

EQL Not yet run
unverified (harvested, no recorded run)
zzmtsvv/rl_task/eql/eql.py
pointer only (licence: NONE) · get_code("d8b7c19096ade30e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zzmtsvv/rl_task 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.

XQLPolicy Not yet run
unverified (harvested, no recorded run)
typoverflow/OfflineRL-Lib/offlinerllib/policy/model_free/xql.py
code served (permissive licence) · get_code("3672c9f7dca8c12c")
How it ran

no invocation recorded.

grad_gumbel Not yet run
unverified (harvested, no recorded run)
typoverflow/OfflineRL-Lib/offlinerllib/policy/model_free/xql.py
code served (permissive licence) · get_code("099b7f3529fc91c2")
How it ran

no invocation recorded.

gumbel_log_loss Not yet run
unverified (harvested, no recorded run)
typoverflow/OfflineRL-Lib/offlinerllib/policy/model_free/xql.py
code served (permissive licence) · get_code("b9154c9068739993")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 10 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
EnsembledCritic
brick of this paper's assembly: model
4 other papers
3 dated earlier, 1 later · 2 only as an assembly brick
1906.00949 (2019-06)
Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction
2110.01548 (2021-10)
Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble
2110.06169 (2021-10)
Offline Reinforcement Learning with Implicit Q-Learning
and 1 more not named here
EnsembledLinear
brick of this paper's assembly: helper
4 other papers
3 dated earlier, 1 later · 2 only as an assembly brick
2110.06169 (2021-10)
Offline Reinforcement Learning with Implicit Q-Learning
2206.04745 (2022-06)
Mildly Conservative Q-Learning for Offline Reinforcement Learning
2208.06193 (2022-08)
Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning
and 1 more not named here
ValueFunction
brick of this paper's assembly: model
2 other papers
1 dated earlier, 1 later · 2 only as an assembly brick
2110.06169 (2021-10)
Offline Reinforcement Learning with Implicit Q-Learning
2310.12955 (2023-10)
Towards Robust Offline Reinforcement Learning under Diverse Data Corruption

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

Modern Deep Reinforcement Learning (RL) algorithms require estimates of the maximal Q-value, which are difficult to compute in continuous domains with an infinite number of possible actions. In this work, we introduce a new update rule for online and offline RL which directly models the maximal value using Extreme Value Theory (EVT), drawing inspiration from economics. By doing so, we avoid computing Q-values using out-of-distribution actions which is often a substantial source of error. Our key insight is to introduce an objective that directly estimates the optimal soft-value functions (LogSumExp) in the maximum entropy RL setting without needing to sample from a policy. Using EVT, we derive our Extreme Q-Learning framework and consequently online and, for the first time, offline MaxEnt Q-learning algorithms, that do not explicitly require access to a policy or its entropy. Our method obtains consistently strong performance in the D4RL benchmark, outperforming prior works by 10+ points on the challenging Franka Kitchen tasks while offering moderate improvements over SAC and TD3 on online DM Control tasks. Visualizations and code can be found on our website 1 .

For agents

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

get_harvested_code_for_paper("2301.02328")
get_code_for_paper("2301.02328")
have("2301.02328")

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

curl https://syntology.ai/api/ran/2301.02328.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.02328.svg)](https://syntology.ai/paper/2301.02328)

Connect an agent — have() is free.