Pith. sign in

REVIEW 1 cited by

Accelerating exploration and representation learning with offline pre-training

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 2304.00046 v1 pith:HHEYODLF submitted 2023-03-31 cs.LG cs.AI

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

Sequential decision-making agents struggle with long horizon tasks, since solving them requires multi-step reasoning. Most reinforcement learning (RL) algorithms address this challenge by improved credit assignment, introducing memory capability, altering the agent's intrinsic motivation (i.e. exploration) or its worldview (i.e. knowledge representation). Many of these components could be learned from offline data. In this work, we follow the hypothesis that exploration and representation learning can be improved by separately learning two different models from a single offline dataset. We show that learning a state representation using noise-contrastive estimation and a model of auxiliary reward separately from a single collection of human demonstrations can significantly improve the sample efficiency on the challenging NetHack benchmark. We also ablate various components of our experimental setting and highlight crucial insights.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Disentangling Exploration of Large Language Models by Optimal Exploitation

    cs.LG 2025-01 conditional novelty 6.0 of 10

    Exploration by LLM agents can be measured separately from exploitation using an optimal exploitation oracle, and most models explore poorly, with exploration performance correlated to reasoning ability.

Pith tools