3 papers
cs.LG2026
From Ticks to Flows: Dynamics of Neural Reinforcement Learning in Continuous Environments
Saket Tiwari, Tejas Kotwal, George Konidaris
We present a novel theoretical framework for deep reinforcement learning (RL) in continuous environments by modeling the problem as a continuous-time stochastic process, drawing on…
cs.LG2026
Spectral Collapse Drives Loss of Plasticity in Deep Continual Learning
Arjun Prakash, Naicheng He, Kaicheng Guo +5
We investigate why deep neural networks suffer from loss of plasticity in continual learning, and thus fail to learn new tasks without reinitializing parameters. We show that this…
cs.LG2025
Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces
Saket Tiwari, Omer Gottesman, George Konidaris
Advances in reinforcement learning (RL) have led to its successful application in complex tasks with continuous state and action spaces. Despite these advances in practice, most th…