Expert Selection in High-Dimensional Markov Decision Processes.
Vicenç Rúbies RoyoEric MazumdarRoy DongClaire J. TomlinS. Shankar SastryPublished in: CDC (2020)
Keyphrases
- markov decision processes
- high dimensional
- optimal policy
- transition matrices
- finite state
- policy iteration
- state space
- reinforcement learning
- reachability analysis
- dynamic programming
- average reward
- partially observable
- decision processes
- decision theoretic planning
- reinforcement learning algorithms
- risk sensitive
- factored mdps
- finite horizon
- policy evaluation
- planning under uncertainty
- action space
- average cost
- state and action spaces
- action sets
- reward function
- semi markov decision processes
- infinite horizon
- markov decision process
- interval estimation