Parental Guidance: Evolutionary Distillation for Non-Prehensile Mobile Manipulation

Zhengyu Zhang, Quanquan Peng, Rosario Scalise, Byron Boots

Keywords: evolutionary robotics, continual learning, non-prehensile manipulation, deep reinforcement learning, imitation learning

TL;DR: we show an effective strategy to compress diverse solutions and progress in solving non-prehensile mobile manipulation tasks via open ended evolution.

Abstract: 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.

Submission Number: 47