Markov decision processes with multidimensional action spaces.
Dimitrios G. PandelisPublished in: Eur. J. Oper. Res. (2010)
Keyphrases
- markov decision processes
- action space
- state and action spaces
- state space
- reinforcement learning
- optimal policy
- finite state
- continuous state
- planning under uncertainty
- control policies
- policy iteration
- markov decision process
- average cost
- decision processes
- continuous state spaces
- reinforcement learning algorithms
- partially observable
- finite horizon
- dynamic programming
- machine learning
- infinite horizon
- heuristic search
- average reward
- reward function
- real valued
- stochastic games
- markov decision problems
- sufficient conditions