ICMLMay, 2023

多任务分层对抗逆强化学习

TL;DRMulti-task Hierarchical Adversarial Inverse Reinforcement Learning (MH-AIRL) is developed to learn hierarchically-structured multi-task policies that are more beneficial for compositional tasks with long horizons and has higher expert data efficiency; MH-AIRL synthesizes context-based multi-task learning, AIRL (an IL approach), and hierarchical policy learning, and evaluations on challenging multi-task settings demonstrate superior performance and transferability of the multi-task policies learned with MH-AIRL compared to SOTA MIL baselines.