Task-Agnostic Morphology Evolution

TL;DR

This paper introduces TAME, a task-agnostic method for evolving agent morphologies using an information-theoretic objective, enabling generalization across tasks without reward-based optimization.

Contribution

TAME is a novel approach that evolves morphologies without task-specific rewards, promoting generalization and reducing optimization costs.

Findings

TAME matches multi-task performance of reward-based methods.

Effective across 2D, 3D, and manipulation environments.

Evolves diverse, task-agnostic morphologies.

Abstract

Deep reinforcement learning primarily focuses on learning behavior, usually overlooking the fact that an agent's function is largely determined by form. So, how should one go about finding a morphology fit for solving tasks in a given environment? Current approaches that co-adapt morphology and behavior use a specific task's reward as a signal for morphology optimization. However, this often requires expensive policy optimization and results in task-dependent morphologies that are not built to generalize. In this work, we propose a new approach, Task-Agnostic Morphology Evolution (TAME), to alleviate both of these issues. Without any task or reward specification, TAME evolves morphologies by only applying randomly sampled action primitives on a population of agents. This is accomplished using an information-theoretic objective that efficiently ranks agents by their ability to reach diverse states in the environment and the causality of their actions. Finally, we empirically demonstrate that across 2D, 3D, and manipulation environments TAME can evolve morphologies that match the multi-task performance of those learned with task supervised algorithms. Our code and videos can be found at https://sites.google.com/view/task-agnostic-evolution.