Pith. sign in

REVIEW

Differentiable Architecture Search for 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 2106.02229 v4 pith:3TAMBJEX submitted 2021-06-04 cs.LG cs.AIcs.CV

Differentiable Architecture Search for Reinforcement Learning

classification cs.LG cs.AIcs.CV
keywords architecturedartsdiscretesearcharchitecturesonlyablationachieve
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In this paper, we investigate the fundamental question: To what extent are gradient-based neural architecture search (NAS) techniques applicable to RL? Using the original DARTS as a convenient baseline, we discover that the discrete architectures found can achieve up to 250% performance compared to manual architecture designs on both discrete and continuous action space environments across off-policy and on-policy RL algorithms, at only 3x more computation time. Furthermore, through numerous ablation studies, we systematically verify that not only does DARTS correctly upweight operations during its supernet phrase, but also gradually improves resulting discrete cells up to 30x more efficiently than random search, suggesting DARTS is surprisingly an effective tool for improving architectures in RL.

discussion (0)

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