Adversarial Feature Training for Generalizable Robotic Visuomotor Control

by   Xi Chen, et al.

Deep reinforcement learning (RL) has enabled training action-selection policies, end-to-end, by learning a function which maps image pixels to action outputs. However, it's application to visuomotor robotic policy training has been limited because of the challenge of large-scale data collection when working with physical hardware. A suitable visuomotor policy should perform well not just for the task-setup it has been trained for, but also for all varieties of the task, including novel objects at different viewpoints surrounded by task-irrelevant objects. However, it is impractical for a robotic setup to sufficiently collect interactive samples in a RL framework to generalize well to novel aspects of a task. In this work, we demonstrate that by using adversarial training for domain transfer, it is possible to train visuomotor policies based on RL frameworks, and then transfer the acquired policy to other novel task domains. We propose to leverage the deep RL capabilities to learn complex visuomotor skills for uncomplicated task setups, and then exploit transfer learning to generalize to new task domains provided only still images of the task in the target domain. We evaluate our method on two real robotic tasks, picking and pouring, and compare it to a number of prior works, demonstrating its superiority.


page 1

page 6


Deep Adversarial Reinforcement Learning for Object Disentangling

Deep learning in combination with improved training techniques and high ...

Learning Generalizable Pivoting Skills

The skill of pivoting an object with a robotic system is challenging for...

Domain Adaptation for Reinforcement Learning on the Atari

Deep reinforcement learning agents have recently been successful across ...

Autonomous learning of multiple, context-dependent tasks

When facing the problem of autonomously learning multiple tasks with rei...

Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes

We study the problem of robotic stacking with objects of complex geometr...

Entropic Policy Composition with Generalized Policy Improvement and Divergence Correction

Deep reinforcement learning (RL) algorithms have made great strides in r...

Deep RL at Scale: Sorting Waste in Office Buildings with a Fleet of Mobile Manipulators

We describe a system for deep reinforcement learning of robotic manipula...

Please sign up or login with your details

Forgot password? Click here to reset