Continuous-Time Markov Decision Processes with Exponential Utility.
Yi ZhangPublished in: SIAM J. Control. Optim. (2017)
Keyphrases
- markov decision processes
- state space
- discount factor
- optimal policy
- markov chain
- reinforcement learning
- dynamic programming
- decision diagrams
- finite state
- transition matrices
- decision theoretic planning
- policy iteration
- stationary policies
- reinforcement learning algorithms
- finite horizon
- markov decision process
- dynamical systems
- planning under uncertainty
- model based reinforcement learning
- reachability analysis
- factored mdps
- decision processes
- heuristic search
- risk sensitive
- utility function
- optimal control
- average cost
- partially observable
- action space
- infinite horizon
- stochastic processes
- state and action spaces
- semi markov decision processes
- expected utility
- efficient computation
- decision making