Improving Policy Optimization with Generalist-Specialist Learning.

Zhiwei Jia Xuanlin Li Zhan Ling Shuang Liu Yiran Wu Hao Su

Published in: ICML (2022)

Keyphrases

learning process
learning algorithm
reinforcement learning
knowledge acquisition
prior knowledge
supervised learning
optimization problems
empirical studies
optimization algorithm
learning problems
global optimization
incremental learning
constrained optimization
learning scheme
kernel machines
directly optimize