Foundations of probability-raising causality in Markov decision processes.
Christel BaierJakob PiribauerRobin ZiemekPublished in: CoRR (2022)
Keyphrases
- markov decision processes
- optimal policy
- state space
- finite state
- reinforcement learning
- dynamic programming
- transition matrices
- policy iteration
- decision theoretic planning
- probability distribution
- decision processes
- markov decision process
- reachability analysis
- action sets
- risk sensitive
- action space
- partially observable
- average reward
- planning under uncertainty
- reinforcement learning algorithms
- average cost
- probabilistic planning
- model based reinforcement learning
- state abstraction
- infinite horizon
- state and action spaces
- expected reward
- multistage
- stochastic shortest path
- data mining
- optimality criterion
- conditional probabilities
- machine learning