Solving Hybrid Markov Decision Processes.
Alberto ReyesLuis Enrique SucarEduardo F. MoralesPablo H. IbargüengoytiaPublished in: MICAI (2006)
Keyphrases
- markov decision processes
- transition matrices
- semi markov decision processes
- optimal policy
- state space
- finite state
- markov decision problems
- dynamic programming
- reinforcement learning
- factored mdps
- policy iteration algorithm
- decision theoretic planning
- policy iteration
- average reward
- average cost
- stochastic shortest path
- planning under uncertainty
- decision processes
- risk sensitive
- action space
- finite horizon
- partially observable
- action sets
- reachability analysis
- reinforcement learning algorithms
- model based reinforcement learning
- state and action spaces
- reward function
- markov decision process
- optimal control
- machine learning