On probability-raising causality in Markov decision processes.
Christel BaierFlorian FunkeJakob PiribauerRobin ZiemekPublished in: FoSSaCS (2022)
Keyphrases
- markov decision processes
- optimal policy
- finite state
- policy iteration
- state space
- dynamic programming
- planning under uncertainty
- partially observable
- reinforcement learning
- infinite horizon
- transition matrices
- reinforcement learning algorithms
- reachability analysis
- expected reward
- average reward
- finite horizon
- decision processes
- factored mdps
- decision theoretic planning
- action space
- risk sensitive
- state and action spaces
- optimality criterion
- average cost
- stationary policies
- state abstraction
- action sets
- model based reinforcement learning
- stochastic shortest path