Model-Free Reinforcement Learning for Stochastic Parity Games

DOI10.4230/LIPIcs.CONCUR.2020.21OpenAlexW3082540285MaRDI QIDQ5089286

Mateo Perez, Dominik Wojtczak, Fabio Somenzi, Sven Schewe, Ashutosh Trivedi, Ernst Moritz Hahn

Publication date: 18 July 2022

Full work available at URL: https://doi.org/10.4230/lipics.concur.2020.21

zbMATH Keywords

stochastic gamesreinforcement learningomega-regular objectives

Mathematics Subject Classification ID

Models and methods for concurrent and distributed computing (process algebras, bisimulation, transition nets, etc.) (68Q85)

Related Items

An impossibility result in automata-theoretic reinforcement learning, A framework for transforming specifications in reinforcement learning, Alternating good-for-MDPs automata, Specification-guided reinforcement learning

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A game of cops and robbers
• Reduction of stochastic parity to stochastic mean-payoff games
• The complexity of stochastic games
• \({\mathcal Q}\)-learning
• The Complexity of Solving Stochastic Games on Graphs
• The complexity of probabilistic verification
• A Simple Algorithm for Solving Qualitative Probabilistic Parity Games
• Limit-Deterministic Büchi Automata for Linear Temporal Logic
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
• Good-for-MDPs Automata for Probabilistic Analysis and Reinforcement Learning
• Computer Science Logic
• Lazy probabilistic model checking without determinisation
• Tools and Algorithms for the Construction and Analysis of Systems
• Stochastic Games