Watch, Try, Learn: Meta-Learning from Demonstrations and Reward

06/07/2019
by   Allan Zhou, et al.
1

Imitation learning allows agents to learn complex behaviors from demonstrations. However, learning a complex vision-based task may require an impractical number of demonstrations. Meta-imitation learning is a promising approach towards enabling agents to learn a new task from one or a few demonstrations by leveraging experience from learning similar tasks. In the presence of task ambiguity or unobserved dynamics, demonstrations alone may not provide enough information; an agent must also try the task to successfully infer a policy. In this work, we propose a method that can learn to learn from both demonstrations and trial-and-error experience with sparse reward feedback. In comparison to meta-imitation, this approach enables the agent to effectively and efficiently improve itself autonomously beyond the demonstration data. In comparison to meta-reinforcement learning, we can scale to substantially broader distributions of tasks, as the demonstration reduces the burden of exploration. Our experiments show that our method significantly outperforms prior approaches on a set of challenging, vision-based control tasks.

READ FULL TEXT

page 2

page 7

page 8

research
04/01/2019

Guided Meta-Policy Search

Reinforcement learning (RL) algorithms have demonstrated promising resul...
research
03/23/2021

Meta-Adversarial Inverse Reinforcement Learning for Decision-making Tasks

Learning from demonstrations has made great progress over the past few y...
research
10/25/2018

One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks

We consider the problem of learning multi-stage vision-based tasks on a ...
research
06/22/2020

PICO: Primitive Imitation for COntrol

In this work, we explore a novel framework for control of complex system...
research
04/02/2021

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

A key challenge in Imitation Learning (IL) is that optimal state actions...
research
07/16/2021

Visual Adversarial Imitation Learning using Variational Models

Reward function specification, which requires considerable human effort ...
research
01/24/2023

Language-guided Task Adaptation for Imitation Learning

We introduce a novel setting, wherein an agent needs to learn a task fro...

Please sign up or login with your details

Forgot password? Click here to reset