Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation.
Yao YaoLi XiaoZhicheng AnWanpeng ZhangDijun LuoPublished in: ICRA (2021)
Keyphrases
- similarity measure
- reinforcement learning
- cost function
- neural network
- probabilistic model
- mathematical model
- high level
- multiple models
- optimal control
- experimental data
- statistical model
- computational model
- theoretical framework
- parameter estimation
- theoretical analysis
- test data
- conceptual model
- objective function
- bayesian networks
- adaptation process
- transition model