Keyphrases
- markov decision processes
- markov games
- stochastic games
- optimal policy
- finite state
- state space
- reinforcement learning
- policy iteration
- dynamic programming
- transition matrices
- reachability analysis
- decision theoretic planning
- factored mdps
- finite horizon
- reinforcement learning algorithms
- action space
- planning under uncertainty
- model based reinforcement learning
- infinite horizon
- partially observable
- markov decision process
- state and action spaces
- state abstraction
- average reward
- decision processes
- search space
- game theory
- machine learning
- action sets
- nash equilibria
- efficient computation
- risk sensitive
- collaborative filtering
- linear programming
- average cost
- reward function
- optimal strategy
- semi markov decision processes
- multistage
- evaluation function