Curriculum Offline Reinforcement Learning.
Yuanying CaiChuheng ZhangHanye ZhaoLi ZhaoJiang BianPublished in: AAMAS (2023)
Keyphrases
- reinforcement learning
- function approximation
- state space
- high school
- reinforcement learning algorithms
- temporal difference
- model free
- multi agent
- machine learning
- temporal difference learning
- professional development
- markov decision processes
- real time
- learning problems
- optimal policy
- multi agent reinforcement learning
- stochastic approximation
- learning process
- learning algorithm
- learning gains
- robotic control
- curriculum development
- reinforcement learning methods
- primary school
- markov decision process
- action selection
- dynamic programming
- optimal control
- transfer learning