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.
Feng Chen, Daniel Kunin, Atsushi Yamamura, and Surya Ganguli
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
This paper defines loss of plasticity via stable manifolds in parameter space and identifies frozen units and cloned-unit manifolds as the main mechanisms that trap gradient trajectories in non-stationary settings.
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.
The authors compare multiple methods for incorporating action information into RNN state updates for RL and report empirical results on illustrative domains.
Operator splitting separates task optimization from proximal stability enforcement to achieve forgetting-free continual learning with SOTA benchmark results.
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.
-
Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity
This paper defines loss of plasticity via stable manifolds in parameter space and identifies frozen units and cloned-unit manifolds as the main mechanisms that trap gradient trajectories in non-stationary settings.
-
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.
-
Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning
The authors compare multiple methods for incorporating action information into RNN state updates for RL and report empirical results on illustrative domains.
-
Task Switching Without Forgetting via Proximal Decoupling
Operator splitting separates task optimization from proximal stability enforcement to achieve forgetting-free continual learning with SOTA benchmark results.