Pith. sign in

REVIEW 5 cited by

Offline Reinforcement Learning as One Big Sequence Modeling Problem

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 2106.02039 v4 pith:6DXSKQK6 submitted 2021-06-03 cs.LG cs.AI

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

Reinforcement learning (RL) is typically concerned with estimating stationary policies or single-step models, leveraging the Markov property to factorize problems in time. However, we can also view RL as a generic sequence modeling problem, with the goal being to produce a sequence of actions that leads to a sequence of high rewards. Viewed in this way, it is tempting to consider whether high-capacity sequence prediction models that work well in other domains, such as natural-language processing, can also provide effective solutions to the RL problem. To this end, we explore how RL can be tackled with the tools of sequence modeling, using a Transformer architecture to model distributions over trajectories and repurposing beam search as a planning algorithm. Framing RL as sequence modeling problem simplifies a range of design decisions, allowing us to dispense with many of the components common in offline RL algorithms. We demonstrate the flexibility of this approach across long-horizon dynamics prediction, imitation learning, goal-conditioned RL, and offline RL. Further, we show that this approach can be combined with existing model-free algorithms to yield a state-of-the-art planner in sparse-reward, long-horizon tasks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 41 citations worldwide. Full citation record

  1. Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills

    cs.RO 2026-08 conditional novelty 6.0 of 10

    A taxonomy of robot learning on a weights-versus-skills axis, with a five-rung self-improvement ladder whose top cell (feedback plus memory plus search) holds only a few recent systems.

  2. Agent-Centric Animal Pose Forecasting

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Agent-centric transformers trained through a composable library reproduce several marginal statistics of courting fly behavior, but discriminators still separate simulated from real flies.

  3. SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text

    cs.AI 2026-05 conditional novelty 6.0 of 10

    A 24-dataset benchmark for inducing schema graphs from raw text, plus an auditable LLM-based pipeline that reports the highest scores on the benchmark's four schema-similarity metrics.

  4. Learning to Ask: Decision Transformers for Adaptive Quantitative Group Testing

    cs.IT 2025-09 reject novelty 5.0 of 10

    An adaptive Decision Transformer policy, trained on heuristic-generated trajectories, is claimed to beat the non-adaptive query-count bound for quantitative group testing.

  5. Energy-Efficient Deep Reinforcement Learning with Spiking Transformers

    cs.LG 2025-05 reject novelty 5.0 of 10

    A spiking Transformer trained on A* maze demonstrations reaches 99.64% action accuracy on a custom 21x21 maze benchmark, but the energy-efficiency and baseline-comparison claims are not backed by proper experiments.

Pith tools