Partial and Conditional Expectations in Markov Decision Processes with Integer Weights.
Jakob PiribauerChristel BaierPublished in: FoSSaCS (2019)
Keyphrases
- markov decision processes
- state space
- finite state
- transition matrices
- optimal policy
- dynamic programming
- policy iteration
- reinforcement learning
- reachability analysis
- model based reinforcement learning
- partially observable
- decision theoretic planning
- risk sensitive
- planning under uncertainty
- linear combination
- average reward
- infinite horizon
- finite horizon
- reinforcement learning algorithms
- state abstraction
- factored mdps
- state and action spaces
- action sets
- action space
- markov decision process
- average cost
- decision processes
- partially observable markov decision processes
- semi markov decision processes