Pith. sign in

REVIEW

Model Based Planning with Energy Based Models

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 1909.06878 v2 pith:2DLVHVGD submitted 2019-09-15 cs.LG cs.ROstat.ML

classification cs.LGcs.ROstat.ML
keywords ebmsstateplanningbetterinferencemodelsonlineenvironment
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Model-based planning holds great promise for improving both sample efficiency and generalization in reinforcement learning (RL). We show that energy-based models (EBMs) are a promising class of models to use for model-based planning. EBMs naturally support inference of intermediate states given start and goal state distributions. We provide an online algorithm to train EBMs while interacting with the environment, and show that EBMs allow for significantly better online learning than corresponding feed-forward networks. We further show that EBMs support maximum entropy state inference and are able to generate diverse state space plans. We show that inference purely in state space - without planning actions - allows for better generalization to previously unseen obstacles in the environment and prevents the planner from exploiting the dynamics model by applying uncharacteristic action sequences. Finally, we show that online EBM training naturally leads to intentionally planned state exploration which performs significantly better than random exploration.

Discussion (0). Continue with ORCID to comment.

Pith tools