Foundations of probability-raising causality in Markov decision processes.
Christel BaierJakob PiribauerRobin ZiemekPublished in: Log. Methods Comput. Sci. (2024)
Keyphrases
- markov decision processes
- state space
- optimal policy
- policy iteration
- finite state
- dynamic programming
- transition matrices
- reinforcement learning
- reachability analysis
- planning under uncertainty
- decision theoretic planning
- average reward
- expected reward
- reinforcement learning algorithms
- probability distribution
- model based reinforcement learning
- action space
- decision processes
- risk sensitive
- factored mdps
- partially observable
- average cost
- markov decision process
- finite horizon
- stationary policies
- state and action spaces
- markov chain
- discounted reward
- infinite horizon
- linear programming