On probability-raising causality in Markov decision processes.
Christel BaierFlorian FunkeJakob PiribauerRobin ZiemekPublished in: CoRR (2022)
Keyphrases
- markov decision processes
- policy iteration
- state space
- reinforcement learning
- finite state
- optimal policy
- transition matrices
- dynamic programming
- reachability analysis
- decision theoretic planning
- decision processes
- factored mdps
- probability distribution
- infinite horizon
- risk sensitive
- average reward
- planning under uncertainty
- average cost
- action space
- partially observable
- finite horizon
- reinforcement learning algorithms
- semi markov decision processes
- model based reinforcement learning
- expected reward
- stochastic shortest path
- markov decision process
- reward function
- real valued
- optimal solution
- objective function