Associative Criteria in Mutually Dependent Markov Decision Processes.
Toshiharu FujitaPublished in: IIAI-AAI (2014)
Keyphrases
- markov decision processes
- mutually dependent
- finite state
- optimal policy
- reinforcement learning
- state space
- dynamic programming
- finite horizon
- transition matrices
- policy iteration
- decision theoretic planning
- random variables
- model based reinforcement learning
- reachability analysis
- factored mdps
- planning under uncertainty
- infinite horizon
- partially observable
- reinforcement learning algorithms
- risk sensitive
- average cost
- decision processes
- state and action spaces
- average reward
- reward function
- markov decision process
- action sets
- linear program