Smooth-Leaky and Randomized Smooth-Leaky activations mitigate loss of plasticity in continual learning by targeting negative-branch shape and saturation behavior.
Smith, Razvan Pascanu, and Claudia Clopath
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
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
-
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.
-
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.