A classification of bisimilarities for general Markov decision processes.
Martín Santiago MoroniPedro Sánchez TerrafPublished in: CoRR (2024)
Keyphrases
- markov decision processes
- state space
- finite state
- optimal policy
- reinforcement learning
- transition matrices
- decision theoretic planning
- special case
- dynamic programming
- policy iteration
- reachability analysis
- partially observable
- support vector
- reinforcement learning algorithms
- decision processes
- action sets
- risk sensitive
- planning under uncertainty
- factored mdps
- infinite horizon
- average reward
- finite horizon
- model based reinforcement learning
- supervised learning
- average cost
- state abstraction
- objective function
- decision problems
- machine learning