TeLAPA maintains archives of behaviorally diverse yet competent policies aligned in a shared latent space to preserve plasticity and enable faster recovery after interference in continual reinforcement learning.
Grown: Grow only when necessary for continual learning.arXiv preprint arXiv:2110.00908
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Newborn units in growing neural networks are forward-active but backward-starved, receiving weaker gradients than existing units and creating integration challenges that make growth less reliable than pruning in complex tasks.
citing papers explorer
-
Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning
TeLAPA maintains archives of behaviorally diverse yet competent policies aligned in a shared latent space to preserve plasticity and enable faster recovery after interference in continual reinforcement learning.
-
On the Stability of Growth in Structural Plasticity
Newborn units in growing neural networks are forward-active but backward-starved, receiving weaker gradients than existing units and creating integration challenges that make growth less reliable than pruning in complex tasks.