Principled Option Learning in Markov Decision Processes.
Roy FoxMichal MoshkovitzNaftali TishbyPublished in: CoRR (2016)
Keyphrases
- markov decision processes
- reinforcement learning
- learning algorithm
- finite state
- model based reinforcement learning
- stochastic games
- state space
- optimal policy
- partially observable
- learning tasks
- dynamic programming
- macro actions
- decision theoretic
- average cost
- policy iteration
- average reward
- planning under uncertainty
- state abstraction
- machine learning