Bridging Action Space Mismatch in Learning from Demonstrations

by   Gautam Salhotra, et al.

Learning from demonstrations (LfD) methods guide learning agents to a desired solution using demonstrations from a teacher. While some LfD methods can handle small mismatches in the action spaces of the teacher and student, here we address the case where the teacher demonstrates the task in an action space that can be substantially different from that of the student – thereby inducing a large action space mismatch. We bridge this gap with a framework, Morphological Adaptation in Imitation Learning (MAIL), that allows training an agent from demonstrations by other agents with significantly different morphologies (from the student or each other). MAIL is able to learn from suboptimal demonstrations, so long as they provide some guidance towards a desired solution. We demonstrate MAIL on challenging household cloth manipulation tasks and introduce a new DRY CLOTH task – cloth manipulation in 3D task with obstacles. In these tasks, we train a visual control policy for a robot with one end-effector using demonstrations from a simulated agent with two end-effectors. MAIL shows up to 27 baselines. It is deployed to a real Franka Panda robot, and can handle multiple variations in cloth properties (color, thickness, size, material) and pose (rotation and translation). We further show generalizability to transfers from n-to-m end-effectors, in the context of a simple rearrangement task.


page 2

page 3

page 6

page 8

page 10

page 11

page 12


Combined Task and Action Learning from Human Demonstrations for Mobile Manipulation Applications

Learning from demonstrations is a promising paradigm for transferring kn...

Eliciting Compatible Demonstrations for Multi-Human Imitation Learning

Imitation learning from human-provided demonstrations is a strong approa...

Practical Robot Learning from Demonstrations using Deep End-to-End Training

Robots need to learn behaviors in intuitive and practical ways for wides...

Learning Online from Corrective Feedback: A Meta-Algorithm for Robotics

A key challenge in Imitation Learning (IL) is that optimal state actions...

Mutual Information Based Knowledge Transfer Under State-Action Dimension Mismatch

Deep reinforcement learning (RL) algorithms have achieved great success ...

Cross Domain Imitation Learning

We study the question of how to imitate tasks across domains with discre...

Learning UI Navigation through Demonstrations composed of Macro Actions

We have developed a framework to reliably build agents capable of UI nav...

Please sign up or login with your details

Forgot password? Click here to reset