Determining the Optimal Strategies for Antagonistic Positional Games in Markov Decision Processes.
Dmitrii LozovanuStefan PicklPublished in: OR (2011)
Keyphrases
- markov decision processes
- optimal strategy
- action sets
- decision problems
- optimal policy
- stochastic games
- game tree
- monte carlo
- state space
- finite state
- reinforcement learning
- dynamic programming
- decision theoretic planning
- infinite horizon
- reinforcement learning algorithms
- average reward
- finite horizon
- average cost
- reachability analysis
- policy iteration
- partially observable
- markov decision process
- transition matrices
- state and action spaces
- planning under uncertainty
- expected cost
- expected utility
- factored mdps
- game theory
- model based reinforcement learning
- mathematical models
- markov chain
- influence diagrams
- stationary policies
- partially observable markov decision processes
- nash equilibria
- decision making
- decision makers
- reward function
- cooperative
- game playing