Image de couverture de livre

Maintaining Plasticity in Deep Continual Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Dohare, Shibhansh, Hernandez-Garcia, J. Fernando, Rahman, Parash, Mahmood, A. Rupam, Sutton, Richard S.
Format:	Preprint
Publié:	2023
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
par: Elsayed, Mohamed, et autres
Publié: (2024)

Reinitializing weights vs units for maintaining plasticity in neural networks
par: Hernandez-Garcia, J. Fernando, et autres
Publié: (2025)

Weight Clipping for Deep Continual and Reinforcement Learning
par: Elsayed, Mohamed, et autres
Publié: (2024)

Streaming Deep Reinforcement Learning Finally Works
par: Elsayed, Mohamed, et autres
Publié: (2024)

Intentional Updates for Streaming Reinforcement Learning
par: Sharifnassab, Arsalan, et autres
Publié: (2026)

Learning Without Time-Based Embodiment Resets in Soft-Actor Critic
par: Farrahi, Homayoon, et autres
Publié: (2025)

Maintaining Plasticity in Continual Learning via Regenerative Regularization
par: Kumar, Saurabh, et autres
Publié: (2023)

Efficient Reinforcement Learning by Reducing Forgetting with Elephant Activation Functions
par: Lan, Qingfeng, et autres
Publié: (2025)

Learning to Optimize for Reinforcement Learning
par: Lan, Qingfeng, et autres
Publié: (2023)

Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning
par: Elsayed, Mohamed, et autres
Publié: (2024)

Distributions as Actions: A Unified Framework for Diverse Action Spaces
par: He, Jiamin, et autres
Publié: (2025)

Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective
par: Wang, Jiuqi, et autres
Publié: (2026)

Average-DICE: Stationary Distribution Correction by Regression
par: Che, Fengdi, et autres
Publié: (2025)

Maintaining Adversarial Robustness in Continuous Learning
par: Ru, Xiaolei, et autres
Publié: (2024)

Revisiting Sparse Rewards for Goal-Reaching Reinforcement Learning
par: Vasan, Gautham, et autres
Publié: (2024)

Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo
par: Ishfaq, Haque, et autres
Publié: (2023)

Plastic Learning with Deep Fourier Features
par: Lewandowski, Alex, et autres
Publié: (2024)

Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks
par: Lee, Hojoon, et autres
Publié: (2024)

Step-size Optimization for Continual Learning
par: Degris, Thomas, et autres
Publié: (2024)

Improving Plasticity in Online Continual Learning via Collaborative Learning
par: Wang, Maorong, et autres
Publié: (2023)

DOLFIN: Balancing Stability and Plasticity in Federated Continual Learning
par: Moussadek, Omayma, et autres
Publié: (2025)

Rethinking Plasticity in Deep Reinforcement Learning
par: He, Zhiqiang
Publié: (2026)

Self-Normalized Resets for Plasticity in Continual Learning
par: Farias, Vivek F., et autres
Publié: (2024)

Sparse Tuning Enhances Plasticity in PTM-based Continual Learning
par: Zhang, Huan, et autres
Publié: (2025)

A Probabilistic Framework for Modular Continual Learning
par: Valkov, Lazar, et autres
Publié: (2023)

More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling
par: Ishfaq, Haque, et autres
Publié: (2024)

Preserving Plasticity in Continual Learning with Adaptive Linearity Injection
par: Rohani, Seyed Roozbeh Razavi, et autres
Publié: (2025)

Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers
par: Vasan, Gautham, et autres
Publié: (2024)

Flashbacks to Harmonize Stability and Plasticity in Continual Learning
par: Mahmoodi, Leila, et autres
Publié: (2025)

Plasticity Loss in Deep Reinforcement Learning: A Survey
par: Klein, Timo, et autres
Publié: (2024)

Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn
par: Tang, Hongyao, et autres
Publié: (2025)

General and Efficient Visual Goal-Conditioned Reinforcement Learning using Object-Agnostic Masks
par: Shahriar, Fahim, et autres
Publié: (2025)

SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning
par: Luo, Lirui, et autres
Publié: (2026)

Optimal Strategies for Federated Learning Maintaining Client Privacy
par: Bhaskar, Uday, et autres
Publié: (2025)

Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning
par: Yuan, Mingqi, et autres
Publié: (2025)

A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
par: Juliani, Arthur, et autres
Publié: (2024)

PLATE: Plasticity-Tunable Efficient Adapters for Geometry-Aware Continual Learning
par: Cosentino, Romain
Publié: (2026)

Beyond Retention: Orchestrating Structural Safety and Plasticity in Continual Learning for LLMs
par: Meng, Fei
Publié: (2026)

Neuro-Informed Adaptive Learning (NIAL) Algorithm: A Hybrid Deep Learning Approach for ECG Signal Classification
par: Rahman, Sowad
Publié: (2025)

Neuron-level Balance between Stability and Plasticity in Deep Reinforcement Learning
par: Lan, Jiahua, et autres
Publié: (2025)