REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer

by   Xingyu Liu, et al.

A popular paradigm in robotic learning is to train a policy from scratch for every new robot. This is not only inefficient but also often impractical for complex robots. In this work, we consider the problem of transferring a policy across two different robots with significantly different parameters such as kinematics and morphology. Existing approaches that train a new policy by matching the action or state transition distribution, including imitation learning methods, fail due to optimal action and/or state distribution being mismatched in different robots. In this paper, we propose a novel method named REvolveR of using continuous evolutionary models for robotic policy transfer implemented in a physics simulator. We interpolate between the source robot and the target robot by finding a continuous evolutionary change of robot parameters. An expert policy on the source robot is transferred through training on a sequence of intermediate robots that gradually evolve into the target robot. Experiments show that the proposed continuous evolutionary model can effectively transfer the policy across robots and achieve superior sample efficiency on new robots using a physics simulator. The proposed method is especially advantageous in sparse reward settings where exploration can be significantly reduced.


page 8

page 13


HERD: Continuous Human-to-Robot Evolution for Learning from Human Demonstration

The ability to learn from human demonstration endows robots with the abi...

Data-driven Policy Transfer with Imprecise Perception Simulation

The paper presents a complete pipeline for learning continuous motion co...

SA-Net: Deep Neural Network for Robot Trajectory Recognition from RGB-D Streams

Learning from demonstration (LfD) and imitation learning offer new parad...

Universal Morphology Control via Contextual Modulation

Learning a universal policy across different robot morphologies can sign...

To Share or Not to Share? Performance Guarantees and the Asymmetric Nature of Cross-Robot Experience Transfer

In the robotics literature, experience transfer has been proposed in dif...

Multi-embodiment Legged Robot Control as a Sequence Modeling Problem

Robots are traditionally bounded by a fixed embodiment during their oper...

Bayesian Gaussian mixture model for robotic policy imitation

A common approach to learn robotic skills is to imitate a policy demonst...

Please sign up or login with your details

Forgot password? Click here to reset