Demonic Variance and a Non-Determinism Score for Markov Decision Processes.
Jakob PiribauerPublished in: MFCS (2024)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- reinforcement learning
- dynamic programming
- transition matrices
- model based reinforcement learning
- reachability analysis
- policy iteration
- finite horizon
- reinforcement learning algorithms
- factored mdps
- decision processes
- planning under uncertainty
- infinite horizon
- action space
- markov decision process
- partially observable
- risk sensitive
- decision theoretic planning
- state and action spaces
- average cost
- action sets
- average reward