Provable Hierarchy-Based Meta-Reinforcement Learning.
Kurtland ChuaQi LeiJason D. LeePublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- optimal policy
- state space
- markov decision processes
- model free
- machine learning
- robotic control
- temporal difference
- learning algorithm
- hierarchical structure
- hierarchical organization
- reinforcement learning algorithms
- action selection
- meta level
- learning classifier systems
- lower level
- higher level
- meta reasoning
- optimal control
- genetic algorithm
- reward function
- learning agents
- stochastic approximation
- transfer learning
- real time