Augmentative Topology Agents For Open-Ended Learning
This addresses the problem of generalization in open-ended learning for AI agents, but it is incremental as it builds on an existing algorithm.
The paper tackles open-ended learning by evolving agents and environments together, allowing agents to increase neural network complexity as environments become harder, resulting in agents that solve more environments than a fixed-topology baseline.
In this work, we tackle the problem of open-ended learning by introducing a method that simultaneously evolves agents and increasingly challenging environments. Unlike previous open-ended approaches that optimize agents using a fixed neural network topology, we hypothesize that generalization can be improved by allowing agents' controllers to become more complex as they encounter more difficult environments. Our method, Augmentative Topology EPOET (ATEP), extends the Enhanced Paired Open-Ended Trailblazer (EPOET) algorithm by allowing agents to evolve their own neural network structures over time, adding complexity and capacity as necessary. Empirical results demonstrate that ATEP results in general agents capable of solving more environments than a fixed-topology baseline. We also investigate mechanisms for transferring agents between environments and find that a species-based approach further improves the performance and generalization of agents.