Abstract Value Iteration for Hierarchical Reinforcement Learning.
Kishor JothimuruganOsbert BastaniRajeev AlurPublished in: AISTATS (2021)
Keyphrases
- hierarchical reinforcement learning
- average reward
- markov decision processes
- markov decision process
- reinforcement learning
- state abstraction
- state space
- model free
- optimal policy
- policy iteration
- reward function
- heuristic search
- search algorithm
- finite state
- dynamic programming
- reinforcement learning algorithms
- long run
- function approximation