Observational Learning
Reinforcement Schedules
Reinforcement
Reproductive Cloning
Generalization, Discrimination, and Extinction
Law of Effect
您也可能阅读
通过共同作者、期刊和引用图与本文相关的文章。
Daolong An1, Chun Shen2, Songlin Li1
1Key Laboratory of Symbolic Computation and Knowledge Engineering (Jilin University), Ministry of Education, Changchun, 130012, China; College of Computer Science and Technology, Jilin University, Changchun, 130012, China.
线下强化学习面临着与分布外 (OOD) 状态和行动的挑战. 结果约束行为克隆 (RCBC) 约束结果状态,改善政策学习和实现最先进的绩效.
科学领域:
背景情况:
研究的目的:
主要方法:
主要成果:
结论: