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