Provable Hierarchy-Based Meta-Reinforcement Learning.
Kurtland ChuaQi LeiJason D. LeePublished in: AISTATS (2023)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- state space
- temporal difference
- optimal policy
- reinforcement learning algorithms
- case study
- learning process
- model free
- meta level
- markov decision processes
- hierarchical structure
- relational reinforcement learning
- temporal difference learning
- lower level
- multi agent
- learning problems
- supervised learning
- dynamic programming
- genetic algorithm
- partially observable
- learning automata
- learning agents
- information retrieval
- hierarchical organization
- machine learning