Sub-policy Adaptation for Hierarchical Reinforcement Learning.
Alexander C. LiCarlos FlorensaIgnasi ClaveraPieter AbbeelPublished in: ICLR (2020)
Keyphrases
- hierarchical reinforcement learning
- reward function
- markov decision process
- average reward
- reinforcement learning
- optimal policy
- model free
- state abstraction
- state space
- markov decision processes
- long run
- policy iteration
- partially observable markov decision processes
- data mining
- artificial neural networks
- generative model
- machine learning