A Kernel Perspective on Behavioural Metrics for Markov Decision Processes.
Pablo Samuel CastroTyler KastnerPrakash PanangadenMark RowlandPublished in: Trans. Mach. Learn. Res. (2023)
Keyphrases
- markov decision processes
- finite state
- state space
- optimal policy
- dynamic programming
- reinforcement learning
- transition matrices
- policy iteration
- decision theoretic planning
- planning under uncertainty
- reachability analysis
- reinforcement learning algorithms
- markov decision process
- average reward
- risk sensitive
- infinite horizon
- kernel function
- finite horizon
- action space
- decision processes
- model based reinforcement learning
- average cost
- partially observable
- reward function
- kernel methods
- state and action spaces
- support vector
- action sets