When Does Neuroevolution Outcompete Reinforcement Learning in Transfer Learning Tasks?

TL;DR

This paper compares neuroevolution and reinforcement learning in transfer learning tasks, introducing new benchmarks and showing that neuroevolution often outperforms RL in transferability and robustness.

Contribution

It introduces two novel benchmarks for transfer learning evaluation and provides empirical evidence that neuroevolution can outperform reinforcement learning in these tasks.

Findings

Neuroevolution methods often outperform RL baselines in transfer tasks.

Transfer capabilities vary significantly among neuroevolution methods.

Neuroevolution shows promise for building more adaptable AI agents.

Abstract

The ability to continuously and efficiently transfer skills across tasks is a hallmark of biological intelligence and a long-standing goal in artificial systems. Reinforcement learning (RL), a dominant paradigm for learning in high-dimensional control tasks, is known to suffer from brittleness to task variations and catastrophic forgetting. Neuroevolution (NE) has recently gained attention for its robustness, scalability, and capacity to escape local optima. In this paper, we investigate an understudied dimension of NE: its transfer learning capabilities. To this end, we introduce two benchmarks: a) in stepping gates, neural networks are tasked with emulating logic circuits, with designs that emphasize modular repetition and variation b) ecorobot extends the Brax physics engine with objects such as walls and obstacles and the ability to easily switch between different robotic morphologies. Crucial in both benchmarks is the presence of a curriculum that enables evaluating skill transfer across tasks of increasing complexity. Our empirical analysis shows that NE methods vary in their transfer abilities and frequently outperform RL baselines. Our findings support the potential of NE as a foundation for building more adaptable agents and highlight future challenges for scaling NE to complex, real-world problems.