Bisimulations and Logical Characterizations on Continuous-Time Markov Decision Processes.
Lei SongLijun ZhangJens Chr. GodskesenPublished in: VMCAI (2014)
Keyphrases
- markov decision processes
- state space
- reinforcement learning
- dynamic programming
- finite state
- stationary policies
- markov chain
- optimal policy
- transition matrices
- optimal control
- infinite horizon
- finite horizon
- policy iteration
- reachability analysis
- reinforcement learning algorithms
- dynamical systems
- action space
- factored mdps
- decision theoretic planning
- decision processes
- markov decision process
- average cost
- risk sensitive
- partially observable
- planning under uncertainty
- state and action spaces
- model based reinforcement learning
- reward function
- planning problems
- action sets
- fixed point
- heuristic search