Pith. sign in

REVIEW 1 cited by

Offline Multi-task Transfer RL with Representational Penalization

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 2402.12570 v1 pith:PDQ5MAPV submitted 2024-02-19 cs.LG cs.AI

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

We study the problem of representation transfer in offline Reinforcement Learning (RL), where a learner has access to episodic data from a number of source tasks collected a priori, and aims to learn a shared representation to be used in finding a good policy for a target task. Unlike in online RL where the agent interacts with the environment while learning a policy, in the offline setting there cannot be such interactions in either the source tasks or the target task; thus multi-task offline RL can suffer from incomplete coverage. We propose an algorithm to compute pointwise uncertainty measures for the learnt representation, and establish a data-dependent upper bound for the suboptimality of the learnt policy for the target task. Our algorithm leverages the collective exploration done by source tasks to mitigate poor coverage at some points by a few tasks, thus overcoming the limitation of needing uniformly good coverage for a meaningful transfer by existing offline algorithms. We complement our theoretical results with empirical evaluation on a rich-observation MDP which requires many samples for complete coverage. Our findings illustrate the benefits of penalizing and quantifying the uncertainty in the learnt representation.

Discussion (0). Sign in 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. Sampling-Based System Identification with Active Exploration for Legged Robot Sim2Real Learning

    cs.RO 2025-05 conditional novelty 7.0 of 10

    SPI-Active identifies legged-robot physical parameters via massive parallel sampling and uses Fisher-information-optimal command sequences to collect informative real-world data, improving sim-to-real transfer on quad...

Pith tools