The Empirical Bayes Envelope and Regret Minimization in Competitive Markov Decision Processes.
Shie MannorNahum ShimkinPublished in: Math. Oper. Res. (2003)
Keyphrases
- markov decision processes
- empirical bayes
- regret minimization
- finite state
- state space
- nash equilibrium
- transition matrices
- optimal policy
- game theoretic
- finite horizon
- dynamic programming
- infinite horizon
- policy iteration
- reinforcement learning
- average cost
- reinforcement learning algorithms
- factored mdps
- model based reinforcement learning
- reachability analysis
- average reward
- action sets
- decision theoretic planning
- markov decision process
- least squares
- multi agent learning
- state and action spaces
- reward function
- real time dynamic programming
- planning under uncertainty
- game theory
- action space
- partially observable