Rethinking Plasticity in Deep Reinforcement Learning

• URL: http://arxiv.org/abs/2603.21173v1
• Date: Sun, 22 Mar 2026 11:27:16 GMT
• Title: Rethinking Plasticity in Deep Reinforcement Learning
• Abstract summary: This paper investigates the fundamental mechanisms driving plasticity loss in deep reinforcement learning (RL)<n>We propose the Optimization-Centric Plasticity (OCP) hypothesis, which posits that plasticity loss arises because optimal points from previous tasks become poor local optima for new tasks.<n>Our findings provide a rigorous optimization-based framework for understanding and restoring network plasticity in complex domains.
• Score: 3.18807491942654
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: This paper investigates the fundamental mechanisms driving plasticity loss in deep reinforcement learning (RL), a critical challenge where neural networks lose their ability to adapt to non-stationary environments. While existing research often relies on descriptive metrics like dormant neurons or effective rank, these summaries fail to explain the underlying optimization dynamics. We propose the Optimization-Centric Plasticity (OCP) hypothesis, which posits that plasticity loss arises because optimal points from previous tasks become poor local optima for new tasks, trapping parameters during task transitions and hindering subsequent learning. We theoretically establish the equivalence between neuron dormancy and zero-gradient states, demonstrating that the absence of gradient signals is the primary driver of dormancy. Our experiments reveal that plasticity loss is highly task-specific; notably, networks with high dormancy rates in one task can achieve performance parity with randomly initialized networks when switched to a significantly different task, suggesting that the network's capacity remains intact but is inhibited by the specific optimization landscape. Furthermore, our hypothesis elucidates why parameter constraints mitigate plasticity loss by preventing deep entrenchment in local optima. Validated across diverse non-stationary scenarios, our findings provide a rigorous optimization-based framework for understanding and restoring network plasticity in complex RL domains.

Related papers

• Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective [41.50730100158907]
  We take a practical view to interpret plasticity as trainability, i.e., a neural network's future optimization gain on a target task.<n>We propose a novel metric, called optimization readiness, which combines gradient strength and gradient reliability.
  arXiv  Detail & Related papers  (2026-05-09T16:35:00Z)
• The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning [62.72522261010872]
  Deep reinforcement learning (RL) suffers from plasticity loss severely due to the nature of non-stationarity.<n>We study the plasticity loss problem from the theoretical perspective of network optimization.<n>We propose Sample Weight Decay -- a lightweight method to restore gradient magnitude.
  arXiv  Detail & Related papers  (2026-04-02T11:29:46Z)
• Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning [57.3885832382455]
  We show that introducing static network sparsity alone can unlock further scaling potential beyond dense counterparts with state-of-the-art architectures.<n>Our analysis reveals that, in contrast to naively scaling up dense DRL networks, such sparse networks achieve both higher parameter efficiency for network expressivity.
  arXiv  Detail & Related papers  (2025-06-20T17:54:24Z)
• Understanding and Exploiting Plasticity for Non-stationary Network Resource Adaptation [7.036243456626816]
  We show that neural networks suffer from plasticity loss, significantly impeding their ability to adapt to evolving network conditions.<n>We propose the Reset Silent Neuron (ReSiN), which preserves neural plasticity through strategic neuron resets guided by both forward and backward propagation states.<n>In our implementation of an adaptive video streaming system, ReSiN has shown significant improvements over existing solutions.
  arXiv  Detail & Related papers  (2025-05-02T21:03:03Z)
• Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning [122.67854581396578]
  Plasticine is an open-source framework for benchmarking plasticity optimization in deep reinforcement learning.<n>Plasticine provides single-file implementations of over 13 mitigation methods, 10 evaluation metrics, and learning scenarios.
  arXiv  Detail & Related papers  (2025-04-24T12:32:13Z)
• Disentangling the Causes of Plasticity Loss in Neural Networks [55.23250269007988]
  We show that loss of plasticity can be decomposed into multiple independent mechanisms. We show that a combination of layer normalization and weight decay is highly effective at maintaining plasticity in a variety of synthetic nonstationary learning tasks.
  arXiv  Detail & Related papers  (2024-02-29T00:02:33Z)
• On the Dynamics Under the Unhinged Loss and Beyond [104.49565602940699]
  We introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze closed-form dynamics. The unhinged loss allows for considering more practical techniques, such as time-vary learning rates and feature normalization.
  arXiv  Detail & Related papers  (2023-12-13T02:11:07Z)
• Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages [56.98243487769916]
  Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning. We propose Adaptive RR, which dynamically adjusts the replay ratio based on the critic's plasticity level.
  arXiv  Detail & Related papers  (2023-10-11T12:05:34Z)
• Understanding plasticity in neural networks [41.79540750236036]
  Plasticity is the ability of a neural network to quickly change its predictions in response to new information. Deep neural networks are known to lose plasticity over the course of training even in relatively simple learning problems.
  arXiv  Detail & Related papers  (2023-03-02T18:47:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.