Pith. sign in

REVIEW 1 cited by

Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised 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 2404.03774 v1 pith:2JCTQL2L submitted 2024-04-04 cs.LG cs.CCcs.CRcs.DS

classification cs.LGcs.CCcs.CRcs.DS
keywords learningcomputationallysupervisedblockmdpsregressionassociatedeasy
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Supervised learning is often computationally easy in practice. But to what extent does this mean that other modes of learning, such as reinforcement learning (RL), ought to be computationally easy by extension? In this work we show the first cryptographic separation between RL and supervised learning, by exhibiting a class of block MDPs and associated decoding functions where reward-free exploration is provably computationally harder than the associated regression problem. We also show that there is no computationally efficient algorithm for reward-directed RL in block MDPs, even when given access to an oracle for this regression problem. It is known that being able to perform regression in block MDPs is necessary for finding a good policy; our results suggest that it is not sufficient. Our separation lower bound uses a new robustness property of the Learning Parities with Noise (LPN) hardness assumption, which is crucial in handling the dependent nature of RL data. We argue that separations and oracle lower bounds, such as ours, are a more meaningful way to prove hardness of learning because the constructions better reflect the practical reality that supervised learning by itself is often not the computational bottleneck.

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. Provable Partially Observable Reinforcement Learning with Privileged Information

    cs.LG 2024-12 conditional novelty 7.0 of 10

    The paper gives the first provable polynomial-sample and quasi-polynomial-time guarantees for expert distillation and belief-weighted asymmetric actor-critic in POMDPs with privileged state information.

Pith tools