paper-with-me

Papers

The Dormant Neuron Phenomenon in Deep Reinforcement Learning

2023-02-24 · Ghada Sokar, Rishabh Agarwal, Pablo Samuel Castro, Utku Evci

In this work we identify the dormant neuron phenomenon in deep reinforcement learning, where an agent's network suffers from an increasing number of inactive neurons, thereby affecting network expressivity. We demonstrate the presence of this phenomenon across a variety of algorithms and environments, and highlight its effect on learning. To address this issue, we propose a simple and effective method (ReDo) that Recycles Dormant neurons throughout training. Our experiments demonstrate that ReDo maintains the expressive power of networks by reducing the number of dormant neurons and results in improved performance.

📄 PDF Abstract BibTeX arXiv:2302.12902

Code (3)

google/dopamine 공식 구현 tf
ZiyiZhang27/tdpo pytorch
timoklein/redo pytorch

Tasks

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Mastering Continual Reinforcement Learning through Fine-Grained Sparse Network Allocation and Dormant Neuron Exploration

2025-03-07 · Chengqi Zheng, Haiyan Yin, Jianda Chen, Terence Ng 외

Continual Reinforcement Learning (CRL) is essential for developing agents that can learn, adapt, and accumulate knowledge over time. However, a fundamental challenge persists as agents must strike a delicate balance betw…

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization

2023-10-30 · Guowei Xu, Ruijie Zheng, Yongyuan Liang, Xiyao Wang 외

Visual reinforcement learning (RL) has shown promise in continuous control tasks. Despite its progress, current algorithms are still unsatisfactory in virtually every aspect of the performance such as sample efficiency, …

continuous-controlContinuous Controlreinforcement-learningReinforcement Learning+1

Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning

2025-05-29 · Jiashun Liu, Zihao Wu, Johan Obando-Ceron, Pablo Samuel Castro 외

Deep reinforcement learning (RL) agents frequently suffer from neuronal activity loss, which impairs their ability to adapt to new data and learn continually. A common method to quantify and address this issue is the tau…

Deep Reinforcement LearningMuJoCoReinforcement Learning (RL)

Neuroplastic Expansion in Deep Reinforcement Learning

2024-10-10 · Jiashun Liu, Johan Obando-Ceron, Aaron Courville, Ling Pan

The loss of plasticity in learning agents, analogous to the solidification of neural pathways in biological brains, significantly impedes learning and adaptation in reinforcement learning due to its non-stationary nature…

Deep Reinforcement LearningMuJoCoreinforcement-learningReinforcement Learning

Condensation of nucleoid in Escherichia coli cell as a result of prolonged starvation

2019-01-31

Electron microscopy and X-ray diffraction studies of dormant E. coli cells revealed several forms of nucleoid condensation: quasi - nanocrystalline, quasi -liquid crystalline (or spore-like) and folded nucleosome - like …