Optimization readiness, defined from gradient strength and reliability, lower-bounds one-step optimization gain and outperforms rank-based diagnostics in predicting neural network trainability across continual learning settings.
Directions of curvature as an explanation for loss of plasticity.arXiv preprint arXiv:2312.00246
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
SPHERE applies a Parseval penalty to MoE policies in continual RL to maintain spectral plasticity, yielding 133% and 50% higher average success on MetaWorld and HumanoidBench versus unregularized MoE baselines.
GXD estimates the first-order functional cost of replacing a neuron via gradient attribution to make adaptive resets more reliable for preserving plasticity in continual learning.
Smooth-Leaky and Randomized Smooth-Leaky activations mitigate loss of plasticity in continual learning by targeting negative-branch shape and saturation behavior.
The paper reframes agentic safety as an epistemic property defined by teachability—the capacity to preserve future corrective leverage—rather than a behavioral property of the current policy.
Survey unifies the definition of plasticity loss in DRL, taxonomizes over 50 mitigations, identifies evaluation gaps, and finds general regularization often outperforms domain-specific methods.
citing papers explorer
-
Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective
Optimization readiness, defined from gradient strength and reliability, lower-bounds one-step optimization gain and outperforms rank-based diagnostics in predicting neural network trainability across continual learning settings.
-
SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning
SPHERE applies a Parseval penalty to MoE policies in continual RL to maintain spectral plasticity, yielding 133% and 50% higher average success on MetaWorld and HumanoidBench versus unregularized MoE baselines.
-
Attribution-Based Neuron Utility for Plasticity Restoration in Deep Networks
GXD estimates the first-order functional cost of replacing a neuron via gradient attribution to make adaptive resets more reliable for preserving plasticity in continual learning.
-
Activation Function Design Sustains Plasticity in Continual Learning
Smooth-Leaky and Randomized Smooth-Leaky activations mitigate loss of plasticity in continual learning by targeting negative-branch shape and saturation behavior.
-
Agentic Safety is an Epistemic Property, Not a Behavioral One
The paper reframes agentic safety as an epistemic property defined by teachability—the capacity to preserve future corrective leverage—rather than a behavioral property of the current policy.
-
Plasticity Loss in Deep Reinforcement Learning: A Survey
Survey unifies the definition of plasticity loss in DRL, taxonomizes over 50 mitigations, identifies evaluation gaps, and finds general regularization often outperforms domain-specific methods.