Pith. sign in

REVIEW 1 cited by

Configurable Markov Decision Processes

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 1806.05415 v1 pith:Q6ILPJUQ submitted 2018-06-14 cs.AI

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

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In many real-world problems, there is the possibility to configure, to a limited extent, some environmental parameters to improve the performance of a learning agent. In this paper, we propose a novel framework, Configurable Markov Decision Processes (Conf-MDPs), to model this new type of interaction with the environment. Furthermore, we provide a new learning algorithm, Safe Policy-Model Iteration (SPMI), to jointly and adaptively optimize the policy and the environment configuration. After having introduced our approach and derived some theoretical results, we present the experimental evaluation in two explicative problems to show the benefits of the environment configurability on the performance of the learned policy.

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. Opponent Aware Reinforcement Learning

    cs.LG 2019-08 conditional novelty 5.0 of 10

    An opponent-aware Q-learning scheme, built on level-k reasoning and Bayesian averaging over adversary types, improves robustness and exploitability in security games and repeated matrix games.

Pith tools