Performance Guarantees for Homomorphisms Beyond Markov Decision Processes.
Sultan Javed MajeedMarcus HutterPublished in: CoRR (2018)
Keyphrases
- markov decision processes
- optimal policy
- dynamic programming
- transition matrices
- finite state
- reinforcement learning
- state space
- policy iteration
- decision theoretic planning
- reachability analysis
- infinite horizon
- planning under uncertainty
- partially observable
- initial state
- average cost
- reinforcement learning algorithms
- finite horizon
- risk sensitive
- factored mdps
- action space
- decision processes
- average reward
- decision diagrams
- reward function