Model-free Reinforcement Learning for Branching Markov Decision Processes.
Ernst Moritz HahnMateo PerezSven ScheweFabio SomenziAshutosh TrivediDominik WojtczakPublished in: CoRR (2021)
Keyphrases
- markov decision processes
- model free reinforcement learning
- reinforcement learning
- finite state
- state space
- optimal policy
- policy gradient
- transition matrices
- reinforcement learning algorithms
- average reward
- decision theoretic planning
- partially observable markov decision processes
- average cost
- policy iteration
- partially observable
- markov decision process
- function approximation
- dynamic programming
- control problems
- stochastic games
- reward function
- machine learning
- infinite horizon
- objective function
- learning algorithm
- monte carlo
- supervised learning
- multi agent
- stochastic shortest path