Pith. sign in

REVIEW

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

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 2212.13936 v1 pith:NHAXDSY6 submitted 2022-12-28 cs.LG cs.AIstat.MEstat.ML

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

classification cs.LG cs.AIstat.MEstat.ML
keywords learningreinforcementkl-regularizedbehavioraldemonstrationsexpertchallengingefficiency
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

KL-regularized reinforcement learning from expert demonstrations has proved successful in improving the sample efficiency of deep reinforcement learning algorithms, allowing them to be applied to challenging physical real-world tasks. However, we show that KL-regularized reinforcement learning with behavioral reference policies derived from expert demonstrations can suffer from pathological training dynamics that can lead to slow, unstable, and suboptimal online learning. We show empirically that the pathology occurs for commonly chosen behavioral policy classes and demonstrate its impact on sample efficiency and online policy performance. Finally, we show that the pathology can be remedied by non-parametric behavioral reference policies and that this allows KL-regularized reinforcement learning to significantly outperform state-of-the-art approaches on a variety of challenging locomotion and dexterous hand manipulation tasks.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.