Augmenting Markov Decision Processes with Advising.
Loïs VanhéeLaurent JeanpierreAbdel-Illah MouaddibPublished in: AAAI (2019)
Keyphrases
- markov decision processes
- optimal policy
- state space
- finite state
- policy iteration
- transition matrices
- dynamic programming
- reinforcement learning
- reachability analysis
- risk sensitive
- infinite horizon
- decision theoretic planning
- average cost
- finite horizon
- average reward
- decision processes
- planning under uncertainty
- partially observable
- model based reinforcement learning
- markov decision process
- reward function
- action space
- factored mdps
- sufficient conditions
- state abstraction
- semi markov decision processes