A taxonomy for similarity metrics between Markov decision processes.
Javier GarcíaÁlvaro VisúsFernando FernándezPublished in: Mach. Learn. (2022)
Keyphrases
- similarity metrics
- markov decision processes
- similarity measure
- similarity metric
- state space
- optimal policy
- finite state
- dynamic programming
- reinforcement learning
- policy iteration
- reinforcement learning algorithms
- reachability analysis
- planning under uncertainty
- transition matrices
- similarity measurement
- average cost
- factored mdps
- decision theoretic planning
- infinite horizon
- model based reinforcement learning
- finite horizon
- average reward
- partially observable
- action space
- euclidean distance
- markov decision process
- action sets
- reward function