Foundational Policy Acquisition via Multitask Learning for Motor Skill Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yamamori, Satoshi, Morimoto, Jun
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916636887351296
author Yamamori, Satoshi
Morimoto, Jun
author_facet Yamamori, Satoshi
Morimoto, Jun
contents In this study, we propose a multitask reinforcement learning algorithm for foundational policy acquisition to generate novel motor skills. \textcolor{\hcolor}{Learning the rich representation of the multitask policy is a challenge in dynamic movement generation tasks because the policy needs to cope with changes in goals or environments with different reward functions or physical parameters. Inspired by human sensorimotor adaptation mechanisms, we developed the learning pipeline to construct the encoder-decoder networks and network selection to facilitate foundational policy acquisition under multiple situations. First, we compared the proposed method with previous multitask reinforcement learning methods in the standard multi-locomotion tasks. The results showed that the proposed approach outperformed the baseline methods. Then, we applied the proposed method to the ball heading task using a monopod robot model to evaluate skill generation performance. The results showed that the proposed method was able to adapt to novel target positions or inexperienced ball restitution coefficients but to acquire a foundational policy network, originally learned for heading motion, which can generate an entirely new overhead kicking skill.
format Preprint
id arxiv_https___arxiv_org_abs_2308_16471
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Foundational Policy Acquisition via Multitask Learning for Motor Skill Generation
Yamamori, Satoshi
Morimoto, Jun
Robotics
Machine Learning
In this study, we propose a multitask reinforcement learning algorithm for foundational policy acquisition to generate novel motor skills. \textcolor{\hcolor}{Learning the rich representation of the multitask policy is a challenge in dynamic movement generation tasks because the policy needs to cope with changes in goals or environments with different reward functions or physical parameters. Inspired by human sensorimotor adaptation mechanisms, we developed the learning pipeline to construct the encoder-decoder networks and network selection to facilitate foundational policy acquisition under multiple situations. First, we compared the proposed method with previous multitask reinforcement learning methods in the standard multi-locomotion tasks. The results showed that the proposed approach outperformed the baseline methods. Then, we applied the proposed method to the ball heading task using a monopod robot model to evaluate skill generation performance. The results showed that the proposed method was able to adapt to novel target positions or inexperienced ball restitution coefficients but to acquire a foundational policy network, originally learned for heading motion, which can generate an entirely new overhead kicking skill.
title Foundational Policy Acquisition via Multitask Learning for Motor Skill Generation
topic Robotics
Machine Learning
url https://arxiv.org/abs/2308.16471