On-Robot Policy Learning with O(2)-Equivariant SAC

03/09/2022
by   Dian Wang, et al.
0

Recently, equivariant neural network models have been shown to be useful in improving sample efficiency for tasks in computer vision and reinforcement learning. This paper explores this idea in the context of on-robot policy learning where a policy must be learned entirely on a physical robotic system without reference to a model, a simulator, or an offline dataset. We focus on applications of SO(2)-Equivariant SAC to robotic manipulation and explore a number of variations of the algorithm. Ultimately, we demonstrate the ability to learn several non-trivial manipulation tasks completely through on-robot experiences in less than an hour or two of wall clock time.

READ FULL TEXT

page 4

page 5

page 6

page 7

page 11

page 12

research
03/11/2022

Graph Neural Networks for Relational Inductive Bias in Vision-based Deep Reinforcement Learning of Robot Control

State-of-the-art reinforcement learning algorithms predominantly learn a...
research
03/10/2020

SQUIRL: Robust and Efficient Learning from Video Demonstration of Long-Horizon Robotic Manipulation Tasks

Recent advances in deep reinforcement learning (RL) have demonstrated it...
research
04/12/2023

Exploiting Symmetry and Heuristic Demonstrations in Off-policy Reinforcement Learning for Robotic Manipulation

Reinforcement learning demonstrates significant potential in automatical...
research
06/12/2022

Reinforcement Learning for Vision-based Object Manipulation with Non-parametric Policy and Action Primitives

The object manipulation is a crucial ability for a service robot, but it...
research
11/19/2020

The Robot Household Marathon Experiment

In this paper, we present an experiment, designed to investigate and eva...
research
06/29/2021

Survivable Robotic Control through Guided Bayesian Policy Search with Deep Reinforcement Learning

Many robot manipulation skills can be represented with deterministic cha...
research
08/10/2019

Learning to Explore in Motion and Interaction Tasks

Model free reinforcement learning suffers from the high sampling complex...

Please sign up or login with your details

Forgot password? Click here to reset