paper-with-me

홈 › Papers

Plasticity Loss in Deep Reinforcement Learning: A Survey

2024-11-07 · Timo Klein, Lukas Miklautz, Kevin Sidak, Claudia Plant, Sebastian Tschiatschek

Akin to neuroplasticity in human brains, the plasticity of deep neural networks enables their quick adaption to new data. This makes plasticity particularly crucial for deep Reinforcement Learning (RL) agents: Once plasticity is lost, an agent's performance will inevitably plateau because it cannot improve its policy to account for changes in the data distribution, which are a necessary consequence of its learning process. Thus, developing well-performing and sample-efficient agents hinges on their ability to remain plastic during training. Furthermore, the loss of plasticity can be connected to many other issues plaguing deep RL, such as training instabilities, scaling failures, overestimation bias, and insufficient exploration. With this survey, we aim to provide an overview of the emerging research on plasticity loss for academics and practitioners of deep reinforcement learning. First, we propose a unified definition of plasticity loss based on recent works, relate it to definitions from the literature, and discuss metrics for measuring plasticity loss. Then, we categorize and discuss numerous possible causes of plasticity loss before reviewing currently employed mitigation strategies. Our taxonomy is the first systematic overview of the current state of the field. Lastly, we discuss prevalent issues within the literature, such as a necessity for broader evaluation, and provide recommendations for future research, like gaining a better understanding of an agent's neural activity and behavior.

📄 PDF Abstract BibTeX arXiv:2411.04832

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Survey

Similar Papers 제목 키워드 기반

SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning

2026-05-06 · Lirui Luo, Guoxi Zhang, Hongming Xu, Cong Fang 외 arxiv

In deep reinforcement learning (DRL), an agent is trained from a stream of experience. In a continual learning setting, such agents can suffer from plasticity loss: their ability to learn new skills from new experiences …

Reinforcement LearningContinual Learning

Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages

2023-10-11 · Guozheng Ma, Lu Li, Sen Zhang, Zixuan Liu 외

Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning (VRL). Although methods like resetting and regularization can potent…

Data Augmentationreinforcement-learning

A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning

2024-05-29 · Arthur Juliani, Jordan T. Ash

Continual learning with deep neural networks presents challenges distinct from both the fixed-dataset and convex continual learning regimes. One such challenge is plasticity loss, wherein a neural network trained in an o…

Continual LearningDeep Reinforcement LearningMontezuma's RevengeReinforcement Learning (RL)

The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning

2026-04-02 · Zihao Wu, Hongyao Tang, Yi Ma, Jiashun Liu 외 arxiv

Deep reinforcement learning (RL) suffers from plasticity loss severely due to the nature of non-stationarity, which impairs the ability to adapt to new data and learn continually. Unfortunately, our understanding of how …

Reinforcement Learning

SingularClip: Preventing Spectral Collapse to Maintain Plasticity in Continual and Reinforcement Learning

2026-08-18 · Tyler Kastner, Nimrod De La Vega, Amir-massoud Farahmand arxiv

Neural networks trained on nonstationary tasks frequently lose the ability to fit new targets, a phenomenon referred to as loss of plasticity. We identify a novel source of plasticity loss due to the growing anisotropy o…

Reinforcement Learning