Model-free reinforcement learning for branching Markov decision processes

DOI10.1007/978-3-030-81688-9_30zbMath1493.93060arXiv2106.06777OpenAlexW3184305164MaRDI QIDQ832301

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

Publication date: 25 March 2022

Full work available at URL: https://arxiv.org/abs/2106.06777

Mathematics Subject Classification ID

Stochastic learning and adaptive control (93E35) Markov and semi-Markov decision processes (90C40) Branching processes (Galton-Watson, birth-and-death, etc.) (60J80)

Uses Software

• PRISM
• OR-tools
• OpenAI Gym

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A strongly polynomial algorithm for criticality of branching processes and consistency of stochastic context-free grammars
• Greatest fixed points of probabilistic min/max polynomial equations, and reachability for branching Markov decision processes
• \({\mathcal Q}\)-learning
• Recursive stochastic games with positive rewards
• A multiple time interval finite state projection algorithm for the solution to the chemical master equation
• Recursive Markov Decision Processes and Recursive Stochastic Games
• Model Checking Stochastic Branching Processes
• On Probabilistic Parallel Programs with Process Creation and Synchronisation
• Recursive Markov chains, stochastic grammars, and monotone systems of nonlinear equations
• Growth Optimality for Branching Markov Decision Chains
• Optimization of Multitype Branching Processes
• Estimation for Discrete Time Branching Processes with Application to Epidemics
• Polynomial Time Algorithms for Branching Markov Decision Processes and Probabilistic Min(Max) Polynomial Bellman Equations
• Branching Processes

This page was built for publication: Model-free reinforcement learning for branching Markov decision processes