Pith. sign in

REVIEW 1 cited by

The $f$-Divergence Reinforcement Learning Framework

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 2109.11867 v2 pith:HPUR5IGC submitted 2021-09-24 cs.LG cs.AI

classification cs.LGcs.AI
keywords policyframeworklearningdivergenceevaluationimprovementreinforcementagents
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

The framework of deep reinforcement learning (DRL) provides a powerful and widely applicable mathematical formalization for sequential decision-making. This paper present a novel DRL framework, termed \emph{$f$-Divergence Reinforcement Learning (FRL)}. In FRL, the policy evaluation and policy improvement phases are simultaneously performed by minimizing the $f$-divergence between the learning policy and sampling policy, which is distinct from conventional DRL algorithms that aim to maximize the expected cumulative rewards. We theoretically prove that minimizing such $f$-divergence can make the learning policy converge to the optimal policy. Besides, we convert the process of training agents in FRL framework to a saddle-point optimization problem with a specific $f$ function through Fenchel conjugate, which forms new methods for policy evaluation and policy improvement. Through mathematical proofs and empirical evaluation, we demonstrate that the FRL framework has two advantages: (1) policy evaluation and policy improvement processes are performed simultaneously and (2) the issues of overestimating value function are naturally alleviated. To evaluate the effectiveness of the FRL framework, we conduct experiments on Atari 2600 video games and show that agents trained in the FRL framework match or surpass the baseline DRL algorithms.

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. Diversity By Design: Leveraging Distribution Matching for Offline Model-Based Optimization

    cs.LG 2025-01 conditional novelty 6.0 of 10

    DynAMO adds a KL distribution-matching term to offline model-based optimization, producing more diverse candidate designs without sacrificing the best-found score.

Pith tools