Maintaining Plasticity in Deep Continual Learning

v1v2v3 (latest)

Maintaining Plasticity in Deep Continual Learning

23 June 2023

Shibhansh Dohare

J. F. Hernandez-Garcia

A. Rupam Mahmood

Richard S. Sutton

ArXiv (abs)PDF HTML HuggingFace (1 upvotes)

Papers citing "Maintaining Plasticity in Deep Continual Learning"

18 / 18 papers shown

Title
Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning Aleksandar Todorov Juan Cardenas-Cartagena Rafael F. Cunha Marco Zullich Matthia Sabatelli CLL 96 1 0 09 Aug 2025
Reinitializing weights vs units for maintaining plasticity in neural networks J. F. Hernandez-Garcia Shibhansh Dohare Jun Luo R. Sutton CLL 205 0 0 31 Jul 2025
Revisiting Clustering of Neural Bandits: Selective Reinitialization for Mitigating Loss of Plasticity Zhiyuan Su Sunhao Dai Xiao Zhang 178 0 0 14 Jun 2025
Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn Hongyao Tang J. Obando-Ceron Pablo Samuel Castro Aaron Courville Glen Berseth 150 3 0 31 May 2025
Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMs Dingkun Zhang Shuhan Qi Xinyu Xiao Kehai Chen Xuan Wang CLL MoMe 257 0 0 08 Mar 2025
Hyperspherical Normalization for Scalable Deep Reinforcement Learning Hojoon Lee Youngdo Lee Takuma Seno Donghu Kim Peter Stone Jaegul Choo 394 9 0 21 Feb 2025
Lightweight Online Adaption for Time Series Foundation Model Forecasts Thomas L. Lee William Toner Rajkarn Singh Artjom Joosem Martin Asenov AI4TS 413 2 0 18 Feb 2025
Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss Sangyeon Park Isaac Han Seungwon Oh Kyung-Joong Kim 359 5 0 03 Feb 2025
Self-Normalized Resets for Plasticity in Continual LearningInternational Conference on Learning Representations (ICLR), 2024 Vivek F. Farias Adam D. Jozefiak CLL 264 4 0 26 Oct 2024
Remove Symmetries to Control Model Expressivity and Improve OptimizationInternational Conference on Learning Representations (ICLR), 2024 Liu Ziyin Yizhou Xu Isaac Chuang AAML 453 4 0 28 Aug 2024
Mitigating the Stability-Plasticity Dilemma in Adaptive Train Scheduling with Curriculum-Driven Continual DQN Expansion Achref Jaziri Etienne Kunzel Visvanathan Ramesh CLL 305 1 0 19 Aug 2024
No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO Skander Moalla Andrea Miele Razvan Pascanu Çağlar Gülçehre 235 16 0 01 May 2024
Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning Mohamed Elsayed A. Rupam Mahmood CLL 288 36 0 31 Mar 2024
Directions of Curvature as an Explanation for Loss of Plasticity Alex Lewandowski Haruto Tanaka Dale Schuurmans Marlos C. Machado 383 16 0 30 Nov 2023
Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization Jack Foster Alexandra Brintrup CLL 315 1 0 15 Sep 2023
Maintaining Plasticity in Continual Learning via Regenerative Regularization Saurabh Kumar Henrik Marklund Benjamin Van Roy CLL KELM 290 34 0 23 Aug 2023
Utility-based Perturbed Gradient Descent: An Optimizer for Continual Learning Mohamed Elsayed A. R. Mahmood CLL 193 8 0 07 Feb 2023
Adaptive Rational Activations to Boost Deep Reinforcement LearningInternational Conference on Learning Representations (ICLR), 2021 Quentin Delfosse P. Schramowski Martin Mundt Alejandro Molina Kristian Kersting 338 22 0 18 Feb 2021