Timezone: »

 
Oral
Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation
Ruohan Wang · Carlo Ciliberto · Pierluigi Vito Amadori · Yiannis Demiris

Tue Jun 11 12:10 PM -- 12:15 PM (PDT) @ Hall B
in Deep RL 1 »

We consider the problem of imitation learning from a finite set of expert trajectories, without access to reinforcement signals. The classical approach of extracting the expert's reward function via inverse reinforcement learning, followed by reinforcement learning is indirect and may be computationally expensive. Recent methods based on generative adversarial networks or generative moment matching formulate the task as distribution matching between the expert policy and the learned policy. However, training via distribution matching could be unstable. We propose a new framework for imitation learning based on estimating the support of the expert policy to compute a fixed reward function from the expert trajectories. This allows us to re-frame imitation learning within the standard reinforcement learning setting. We demonstrate the efficacy of our reward function on both discrete and continuous domains. The policies learned using different reinforcement learning methods with the proposed reward function achieve comparable or better performance than other imitation learning methods.

[ Slides]  [ Video] 

Author Information

Ruohan Wang (Imperial College London)
Carlo Ciliberto (Imperial College London)
Pierluigi Vito Amadori (Imperial College London)
Yiannis Demiris (Imperial College London)

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

More from the Same Authors