Monotonically Improving Limit-Optimal Strategies in Finite-State Decision Processes.
Theodore P. HillJan van der WalPublished in: Math. Oper. Res. (1987)
Keyphrases
- finite state
- decision processes
- optimal strategy
- decision problems
- optimal policy
- markov decision processes
- markov chain
- partially observable markov decision processes
- expected cost
- model checking
- dynamic programming
- state space
- monte carlo
- reinforcement learning
- long run
- utility function
- tree automata
- decision process
- average cost
- computational complexity
- expected utility
- action sets
- reasoning process
- artificial intelligence
- lower bound
- single agent
- decision making
- machine learning
- data mining