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