loading
Documents

Research.Publish.Connect.

Paper

Authors: George Mason 1 ; Radu Calinescu 1 ; Daniel Kudenko 1 and Alec Banks 2

Affiliations: 1 University of York, United Kingdom ; 2 Defence Science and Technology Laboratory, United Kingdom

ISBN: 978-989-758-220-2

Keyword(s): Reinforcement Learning, Safety Constraint Verification, Abstract Markov Decision Processes.

Related Ontology Subjects/Areas/Topics: Agents ; Artificial Intelligence ; Computational Intelligence ; Constraint Satisfaction ; Evolutionary Computing ; Knowledge Discovery and Information Retrieval ; Knowledge-Based Systems ; Machine Learning ; Privacy, Safety and Security ; Soft Computing ; Symbolic Systems ; Uncertainty in AI

Abstract: We present a new reinforcement learning (RL) approach that enables an autonomous agent to solve decision making problems under constraints. Our assured reinforcement learning approach models the uncertain environment as a high-level, abstract Markov decision process (AMDP), and uses probabilistic model checking to establish AMDP policies that satisfy a set of constraints defined in probabilistic temporal logic. These formally verified abstract policies are then used to restrict the RL agent's exploration of the solution space so as to avoid constraint violations. We validate our RL approach by using it to develop autonomous agents for a flag-collection navigation task and an assisted-living planning problem.

PDF ImageFull Text

Download
Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 54.156.51.193

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Mason G., Calinescu R., Kudenko D. and Banks A. (2017). Assured Reinforcement Learning with Formally Verified Abstract Policies.In Proceedings of the 9th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-220-2, pages 105-117. DOI: 10.5220/0006156001050117

@conference{icaart17,
author={George Mason and Radu Calinescu and Daniel Kudenko and Alec Banks},
title={Assured Reinforcement Learning with Formally Verified Abstract Policies},
booktitle={Proceedings of the 9th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2017},
pages={105-117},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006156001050117},
isbn={978-989-758-220-2},
}

TY - CONF

JO - Proceedings of the 9th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Assured Reinforcement Learning with Formally Verified Abstract Policies
SN - 978-989-758-220-2
AU - Mason G.
AU - Calinescu R.
AU - Kudenko D.
AU - Banks A.
PY - 2017
SP - 105
EP - 117
DO - 10.5220/0006156001050117

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.