Pith. sign in

REVIEW 3 cited by

A Survey on Transformers in Reinforcement Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2301.03044 v3 pith:6G3KNXKL submitted 2023-01-08 cs.LG cs.AI

classification cs.LGcs.AI
keywords transformersbeenlearningreinforcementappearedarchitecturebroughtchallenges
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Transformer has been considered the dominating neural architecture in NLP and CV, mostly under supervised settings. Recently, a similar surge of using Transformers has appeared in the domain of reinforcement learning (RL), but it is faced with unique design choices and challenges brought by the nature of RL. However, the evolution of Transformers in RL has not yet been well unraveled. In this paper, we seek to systematically review motivations and progress on using Transformers in RL, provide a taxonomy on existing works, discuss each sub-field, and summarize future prospects.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Generative Optimization for Incentivized Advertising with Global Level Constraints

    cs.LG 2026-08 conditional novelty 5.0 of 10

    Tokenized autoregressive generation of incentive amounts with a lambda-conditioned policy and constraint-aware alignment (SCPO) reports higher revenue, higher ROI, and fewer ROI violations than six baselines on one in...

  2. Prompt-Tuning Bandits: Enabling Few-Shot Generalization for Efficient Multi-Task Offline RL

    cs.LG 2025-02 conditional novelty 5.0 of 10

    A contextual bandit that selects trajectory prompts at inference time improves a frozen Prompting Decision Transformer's performance in a toy multi-task offline RL environment.

  3. Reinforcement Learning in hyperbolic space for multi-step reasoning

    cs.LG 2025-07 reject novelty 4.0 of 10

    Hyperbolic transformer policies are claimed to beat vanilla transformer policies by 32-45% on a handful of reasoning and control problems, but the evidence is too weak to support the claim.

Pith tools