Pith. sign in

REVIEW 1 cited by

Policy-Aware Model Learning for Policy Gradient Methods

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 2003.00030 v2 pith:ABN3JC3O submitted 2020-02-28 cs.AI

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

This paper considers the problem of learning a model in model-based reinforcement learning (MBRL). We examine how the planning module of an MBRL algorithm uses the model, and propose that the model learning module should incorporate the way the planner is going to use the model. This is in contrast to conventional model learning approaches, such as those based on maximum likelihood estimate, that learn a predictive model of the environment without explicitly considering the interaction of the model and the planner. We focus on policy gradient type of planning algorithms and derive new loss functions for model learning that incorporate how the planner uses the model. We call this approach Policy-Aware Model Learning (PAML). We theoretically analyze a generic model-based policy gradient algorithm and provide a convergence guarantee for the optimized policy. We also empirically evaluate PAML on some benchmark problems, showing promising results.

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. Calibrated Value-Aware Model Learning with Probabilistic Environment Models

    cs.LG 2025-05 conditional novelty 8.0 of 10

    MuZero-style value-aware model losses are uncalibrated with stochastic models; the paper derives a variance-corrected CVAML loss and proves deterministic models can be value-equivalent.

Pith tools