Timezone: »

Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy Optimization
Minghuan Liu · Zhengbang Zhu · Yuzheng Zhuang · Weinan Zhang · Jianye Hao · Yong Yu · Jun Wang

Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #835

Recent progress in state-only imitation learning extends the scope of applicability of imitation learning to real-world settings by relieving the need for observing expert actions.However, existing solutions only learn to extract a state-to-action mapping policy from the data, without considering how the expert plans to the target. This hinders the ability to leverage demonstrations and limits the flexibility of the policy.In this paper, we introduce Decoupled Policy Optimization (DePO), which explicitly decouples the policy as a high-level state planner and an inverse dynamics model. With embedded decoupled policy gradient and generative adversarial training, DePO enables knowledge transfer to different action spaces or state transition dynamics, and can generalize the planner to out-of-demonstration state regions.Our in-depth experimental analysis shows the effectiveness of DePO on learning a generalized target state planner while achieving the best imitation performance. We demonstrate the appealing usage of DePO for transferring across different tasks by pre-training, and the potential for co-training agents with various skills.

Author Information

Minghuan Liu (Shanghai Jiao Tong University)
Zhengbang Zhu (Shanghai Jiao Tong University)
Yuzheng Zhuang (HUAWEI)
Weinan Zhang (Shanghai Jiao Tong University)
Jianye Hao (Huawei Noah's Ark Lab)
Yong Yu (Shanghai Jiao Tong University)
Jun Wang (UCL)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors