Continuous-Time Markov Decision Processes with Controlled Observations.
Yunhan HuangVeeraruna KavithaQuanyan ZhuPublished in: CoRR (2019)
Keyphrases
- markov decision processes
- state space
- policy iteration
- finite state
- reinforcement learning
- transition matrices
- optimal policy
- decision theoretic planning
- dynamic programming
- model based reinforcement learning
- planning under uncertainty
- markov chain
- infinite horizon
- reinforcement learning algorithms
- risk sensitive
- stationary policies
- optimal control
- reachability analysis
- average cost
- dynamical systems
- decision processes
- action sets
- finite horizon
- average reward
- factored mdps
- markov decision process
- state and action spaces
- heuristic search
- action space
- decision diagrams