Maximal Cost-Bounded Reachability Probability on Continuous-Time Markov Decision Processes.
Hongfei FuPublished in: CoRR (2013)
Keyphrases
- markov decision processes
- state space
- average cost
- finite state
- optimal policy
- stationary policies
- reinforcement learning
- markov chain
- transition matrices
- policy iteration
- reachability analysis
- dynamic programming
- dynamical systems
- heuristic search
- decision theoretic planning
- risk sensitive
- action space
- planning under uncertainty
- finite horizon
- average reward
- partially observable
- infinite horizon
- long run
- action sets
- reinforcement learning algorithms
- state and action spaces
- factored mdps
- optimal control
- markov decision process
- transition probabilities
- expected cost
- decision processes
- planning problems
- probability distribution
- model based reinforcement learning
- search space
- optimality criterion
- reward function
- belief state
- expected reward
- semi markov decision processes