SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.14550 · ICLR · 2024

When should we prefer Decision Transformers for Offline Reinforcement Learning?

Rohan Chitnis, Amy Zhang, Shagun Sodhani, Alborz Geramifard, Prajjwal Bhargava

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 2 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2305.14550.json · badge: /api/ran/2305.14550.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
prajjwal1/rl_paradigm canonical (classifier label)
classifier basis: census
1 ran · 2 no recorded run
FunctionStatusWhere it lives
discount_cumsum Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
prajjwal1/rl_paradigm/exorl/dataset.py
pointer only (licence: MIT); the stored copy get_code serves, from bkkgbkjb/oppo, is pointer only (licence: NONE) · get_code("0161b27cbe3cc58d")
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 bkkgbkjb/oppo, and GitHub detected no licence in that repository 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.

load_tf_weights_in_gpt2 Not yet run
unverified (harvested, no recorded run)
prajjwal1/rl_paradigm/exorl/models/trajectory_gpt2.py
pointer only (licence: MIT); the stored copy get_code serves, from tencentarc/moto, is pointer only (licence: NOASSERTION) · get_code("00a33466c69c5705")
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 tencentarc/moto, and GitHub could not classify the licence of that repository (NOASSERTION). 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_data Not yet run
unverified (harvested, no recorded run)
prajjwal1/rl_paradigm/atari/read_data.py
code served (permissive licence) · get_code("25de3e2550064897")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 2 the same month, 2 later) and 1 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
load_tf_weights_in_gpt2 22 other papers
7 dated earlier, 2 the same month, 13 later
2106.01345 (2021-06)
Decision Transformer: Reinforcement Learning via Sequence Modeling
2110.06206 (2021-10)
StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning
2202.11705 (2022-02)
COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics
and 19 more not named here
discount_cumsum 17 other papers
9 dated earlier, 1 the same month, 7 later
2106.01345 (2021-06)
Decision Transformer: Reinforcement Learning via Sequence Modeling
2110.06206 (2021-10)
StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning
2111.10364 (2021-11)
Generalized Decision Transformer for Offline Hindsight Information Matching
and 14 more not named here

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

Offline reinforcement learning (RL) allows agents to learn effective, returnmaximizing policies from a static dataset. Three popular algorithms for offline RL are Conservative Q-Learning (CQL), Behavior Cloning (BC), and Decision Transformer (DT), from the class of Q-Learning, Imitation Learning, and Sequence Modeling respectively. A key open question is: which algorithm is preferred under what conditions? We study this question empirically by exploring the performance of these algorithms across the commonly used D4RL and ROBOMIMIC benchmarks. We design targeted experiments to understand their behavior concerning data suboptimality, task complexity, and stochasticity. Our key findings are: (1) DT requires more data than CQL to learn competitive policies but is more robust; (2) DT is a substantially better choice than both CQL and BC in sparse-reward and low-quality data settings; (3) DT and BC are preferable as task horizon increases, or when data is obtained from human demonstrators; and (4) CQL excels in situations characterized by the combination of high stochasticity and low data quality. We also investigate architectural choices and scaling trends for DT on ATARI and D4RL and make design/scaling recommendations. We find that scaling the amount of data for DT by 5x gives a 2.5x average score improvement on ATARI.

For agents

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

get_harvested_code_for_paper("2305.14550")
get_code_for_paper("2305.14550")
have("2305.14550")

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

curl https://syntology.ai/api/ran/2305.14550.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.14550.svg)](https://syntology.ai/paper/2305.14550)

Connect an agent — have() is free.