Parental Guidance: Efficient Lifelong Learning through Evolutionary Distillation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Octi, Peng, Quanquan, Scalise, Rosario, Boots, Bryon
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916660725678080
author Zhang, Octi
Peng, Quanquan
Scalise, Rosario
Boots, Bryon
author_facet Zhang, Octi
Peng, Quanquan
Scalise, Rosario
Boots, Bryon
contents Developing robotic agents that can perform well in diverse environments while showing a variety of behaviors is a key challenge in AI and robotics. Traditional reinforcement learning (RL) methods often create agents that specialize in narrow tasks, limiting their adaptability and diversity. To overcome this, we propose a preliminary, evolution-inspired framework that includes a reproduction module, similar to natural species reproduction, balancing diversity and specialization. By integrating RL, imitation learning (IL), and a coevolutionary agent-terrain curriculum, our system evolves agents continuously through complex tasks. This approach promotes adaptability, inheritance of useful traits, and continual learning. Agents not only refine inherited skills but also surpass their predecessors. Our initial experiments show that this method improves exploration efficiency and supports open-ended learning, offering a scalable solution where sparse reward coupled with diverse terrain environments induces a multi-task setting.
format Preprint
id arxiv_https___arxiv_org_abs_2503_18531
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Parental Guidance: Efficient Lifelong Learning through Evolutionary Distillation
Zhang, Octi
Peng, Quanquan
Scalise, Rosario
Boots, Bryon
Robotics
Machine Learning
Neural and Evolutionary Computing
F.2.2, I.2.7
Developing robotic agents that can perform well in diverse environments while showing a variety of behaviors is a key challenge in AI and robotics. Traditional reinforcement learning (RL) methods often create agents that specialize in narrow tasks, limiting their adaptability and diversity. To overcome this, we propose a preliminary, evolution-inspired framework that includes a reproduction module, similar to natural species reproduction, balancing diversity and specialization. By integrating RL, imitation learning (IL), and a coevolutionary agent-terrain curriculum, our system evolves agents continuously through complex tasks. This approach promotes adaptability, inheritance of useful traits, and continual learning. Agents not only refine inherited skills but also surpass their predecessors. Our initial experiments show that this method improves exploration efficiency and supports open-ended learning, offering a scalable solution where sparse reward coupled with diverse terrain environments induces a multi-task setting.
title Parental Guidance: Efficient Lifelong Learning through Evolutionary Distillation
topic Robotics
Machine Learning
Neural and Evolutionary Computing
F.2.2, I.2.7
url https://arxiv.org/abs/2503.18531