Exponentially Weighted Imitation Learning For Batched Historical Data

Authors:
Qing Wang Tencent AI Lab
Jiechao Xiong Tencent AI Lab
Lei Han
Peng Sun Tencent AI Lab
Han Liu Tencent AI Lab
Tong Zhang Tencent AI Lab

Introduction:

The authors consider deep policy learning with only batched historical trajectories.To solve this problem, the authors propose a monotonic advantage reweighted imitation learning strategy that is applicable to problems with complex nonlinear function approximation and works well with hybrid (discrete and continuous) action space.

Abstract:

We consider deep policy learning with only batched historical trajectories. The main challenge of this problem is that the learner no longer has a simulator or ``environment oracle'' as in most reinforcement learning settings. To solve this problem, we propose a monotonic advantage reweighted imitation learning strategy that is applicable to problems with complex nonlinear function approximation and works well with hybrid (discrete and continuous) action space. The method does not rely on the knowledge of the behavior policy, thus can be used to learn from data generated by an unknown policy. Under mild conditions, our algorithm, though surprisingly simple, has a policy improvement bound and outperforms most competing methods empirically. Thorough numerical results are also provided to demonstrate the efficacy of the proposed methodology.

You may want to know: