AltNet: Addressing the Plasticity-Stability Dilemma in Reinforcement Learning

ArXi:2512.01034v3 Announce Type: replace Artificial neural networks have shown remarkable success in supervised learning when trained on a single task using a fixed dataset. However, when neural networks are trained on a reinforcement learning task, their ability to continue learning from new experiences declines over time. This decline in learning ability is known as plasticity loss. To re plasticity, prior work has explored periodically resetting the parameters of the learning network, a strategy that often improves performance.