Online Learning in Kernelized Markov Decision Processes.
Sayak Ray ChowdhuryAditya GopalanPublished in: CoRR (2018)
Keyphrases
- markov decision processes
- online learning
- state space
- finite state
- dynamic programming
- optimal policy
- reinforcement learning
- transition matrices
- policy iteration
- e learning
- reinforcement learning algorithms
- active learning
- planning under uncertainty
- reachability analysis
- partially observable
- average cost
- finite horizon
- decision theoretic planning
- action sets
- decision processes
- factored mdps
- infinite horizon
- average reward
- kernel function
- discounted reward
- search algorithm
- risk sensitive
- markov decision process