Improving Reward Estimation in Goal-Conditioned Imitation Learning with Counterfactual Data and Structural Causal Models.
HAL (Le Centre pour la Communication Scientifique Directe)（2023）
关键词
imitation learning,reward estimation,structural causal models,counterfactual data,goal-conditioned
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要