Mutually Dependent Markov Decision Processes.
Toshiharu FujitaAkifumi KiraPublished in: J. Adv. Comput. Intell. Intell. Informatics (2014)
Keyphrases
- markov decision processes
- mutually dependent
- transition matrices
- state space
- optimal policy
- reinforcement learning
- finite state
- policy iteration
- reinforcement learning algorithms
- average cost
- finite horizon
- factored mdps
- decision theoretic planning
- model based reinforcement learning
- random variables
- infinite horizon
- average reward
- dynamic programming
- heuristic search
- planning under uncertainty
- action space
- reachability analysis
- decision processes
- multi agent
- action sets
- machine learning
- semi markov decision processes
- markov decision process
- stochastic shortest path