Quality-Diversity Optimization Meets Neuron-Centric Hebbian Learning

In recent years, Hebbian Learning (HL) was employed in several Reinforcement Learning (RL) tasks to maintain high plasticity within the models, while Quality-Diversity (QD) algorithms have been exploited to retrieve diverse high-performing solutions. In this work, we propose a combination of QD algorithms with the recently introduced Neuron-Centric Hebbian Learning (NcHL) to tackle RL tasks. QD methods aim to evolve diverse, high-performing agents’ behaviors, offering enhanced robustness and potentially improving the interpretability of those behaviors, compared to conventional optimization. Moreover, NcHL introduces a scalable HL approach based on neuron-centric local plasticity rules, enabling on-device adaptation without gradient-based updates. We evaluate the proposed framework on three standard RL benchmarks, CartPole, MountainCar, and LunarLander, using three state-of-the-art QD algorithms: MAP-Elites (ME), CMA-ME, and CMA-MAE. Experimental results demonstrate that combining QD with NcHL facilitates the emergence of heterogeneous yet effective control strategies. Behavioral analyses further highlight diverse plasticity dynamics and task-specific adaptation.