Kernel-Based Reinforcement Learning in Robust Markov Decision Processes.
Shiau Hong LimArnaud AutefPublished in: ICML (2019)
Keyphrases
- markov decision processes
- reinforcement learning
- optimal policy
- state space
- reinforcement learning algorithms
- policy iteration
- finite state
- dynamic programming
- model based reinforcement learning
- state and action spaces
- average reward
- infinite horizon
- partially observable
- finite horizon
- decision theoretic planning
- action space
- markov decision process
- average cost
- decision processes
- state abstraction
- transition matrices
- action sets
- factored mdps
- planning under uncertainty
- stochastic games
- markov decision problems
- policy evaluation
- decentralized control
- function approximation
- reward function
- actor critic
- kernel methods
- decision problems
- optimal control
- reachability analysis
- semi markov decision processes
- dynamical systems