Generating Explanations Based on Markov Decision Processes.
Francisco ElizaldeLuis Enrique SucarJulieta NoguezAlberto ReyesPublished in: MICAI (2009)
Keyphrases
- markov decision processes
- generating explanations
- optimal policy
- state space
- finite state
- policy iteration
- reachability analysis
- dynamic programming
- risk sensitive
- transition matrices
- reinforcement learning
- decision theoretic planning
- partially observable
- finite horizon
- reinforcement learning algorithms
- infinite horizon
- decision processes
- markov decision process
- factored mdps
- action space
- average cost
- average reward
- planning under uncertainty
- markov decision problems
- state and action spaces
- action sets
- semi markov decision processes
- multi agent
- machine learning