The Ecosystem Path to General AI

TL;DR

This paper introduces Ecotwin, an open-source ecosystem simulator built on Unity, modeling complex ecosystems with organism cognition, and demonstrates emergent natural phenomena and behaviors through reinforcement learning and reflex networks.

Contribution

The paper presents Ecotwin, a novel ecosystem simulation platform integrating reinforcement learning and reflex networks, enabling the study of emergent ecological behaviors and general AI development.

Findings

Emergence of Lotka-Volterra population dynamics

Diel vertical migration behavior in marine ecosystems

RL combined with reflexes outperforms pure RL agents in dangerous environments

Abstract

We start by discussing the link between ecosystem simulators and general AI. Then we present the open-source ecosystem simulator Ecotwin, which is based on the game engine Unity and operates on ecosystems containing inanimate objects like mountains and lakes, as well as organisms such as animals and plants. Animal cognition is modeled by integrating three separate networks: (i) a reflex network for hard-wired reflexes; (ii) a happiness network that maps sensory data such as oxygen, water, energy, and smells, to a scalar happiness value; and (iii) a policy network for selecting actions. The policy network is trained with reinforcement learning (RL), where the reward signal is defined as the happiness difference from one time step to the next. All organisms are capable of either sexual or asexual reproduction, and they die if they run out of critical resources. We report results from three studies with Ecotwin, in which natural phenomena emerge in the models without being hardwired. First, we study a terrestrial ecosystem with wolves, deer, and grass, in which a Lotka-Volterra style population dynamics emerges. Second, we study a marine ecosystem with phytoplankton, copepods, and krill, in which a diel vertical migration behavior emerges. Third, we study an ecosystem involving lethal dangers, in which certain agents that combine RL with reflexes outperform pure RL agents.