Pith. sign in

REVIEW

Options of Interest: Temporal Abstraction with Interest Functions

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 2001.00271 v1 pith:HNTUUAX3 submitted 2020-01-01 cs.LG cs.AIstat.ML

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

Temporal abstraction refers to the ability of an agent to use behaviours of controllers which act for a limited, variable amount of time. The options framework describes such behaviours as consisting of a subset of states in which they can initiate, an internal policy and a stochastic termination condition. However, much of the subsequent work on option discovery has ignored the initiation set, because of difficulty in learning it from data. We provide a generalization of initiation sets suitable for general function approximation, by defining an interest function associated with an option. We derive a gradient-based learning algorithm for interest functions, leading to a new interest-option-critic architecture. We investigate how interest functions can be leveraged to learn interpretable and reusable temporal abstractions. We demonstrate the efficacy of the proposed approach through quantitative and qualitative results, in both discrete and continuous environments.

Discussion (0). Sign in to comment.

Pith tools