Understanding and Preventing Capacity Loss in Reinforcement Learning

20 April 2022

Papers citing "Understanding and Preventing Capacity Loss in Reinforcement Learning"

50 / 80 papers shown

Title
Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning Mingqi Yuan Qi Wang Guozheng Ma Bo-wen Li Xin Jin Yunbo Wang Xiaokang Yang Wenjun Zeng D. Tao OffRL AI4CE 33 0 0 24 Apr 2025
SparsyFed: Sparse Adaptive Federated Training Adriano Guastella Lorenzo Sani Alex Iacob Alessio Mora Paolo Bellavista Nicholas D. Lane FedML 31 0 0 07 Apr 2025
1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities Kevin Wang Ishaan Javali Michał Bortkiewicz Tomasz Trzciñski Benjamin Eysenbach SSL OffRL 67 0 0 19 Mar 2025
Improving Plasticity in Non-stationary Reinforcement Learning with Evidential Proximal Policy Optimization Abdullah Akgul Gulcin Baykal Manuel Haußmann M. Kandemir 38 0 0 03 Mar 2025
Hyperspherical Normalization for Scalable Deep Reinforcement Learning Hojoon Lee Youngdo Lee Takuma Seno Donghu Kim Peter Stone Jaegul Choo 63 1 0 24 Feb 2025
Learning to Sample Effective and Diverse Prompts for Text-to-Image Generation Taeyoung Yun Dinghuai Zhang Jinkyoo Park Ling Pan DiffM 84 2 0 17 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 62 2 0 03 Feb 2025
Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps Benjamin Ellis Matthew Jackson Andrei Lupu Alexander David Goldie Mattie Fellows Shimon Whiteson Jakob Foerster 77 0 0 22 Dec 2024
Parseval Regularization for Continual Reinforcement Learning Wesley Chung Lynn Cherif D. Meger Doina Precup CLL 78 2 0 10 Dec 2024
Permutation Invariant Learning with High-Dimensional Particle Filters Akhilan Boopathy Aneesh Muppidi Peggy Yang Abhiram Iyer William Yue Ila R Fiete SSL 36 0 0 30 Oct 2024
Plastic Learning with Deep Fourier Features Alex Lewandowski Dale Schuurmans Marlos C. Machado CLL 42 3 0 27 Oct 2024
Self-Normalized Resets for Plasticity in Continual Learning Vivek F. Farias Adam D. Jozefiak CLL 43 0 0 26 Oct 2024
Towards Optimal Adapter Placement for Efficient Transfer Learning Aleksandra I. Nowak Otniel-Bogdan Mercea Anurag Arnab Jonas Pfeiffer Yann N. Dauphin Utku Evci 25 0 0 21 Oct 2024
Streaming Deep Reinforcement Learning Finally Works Mohamed Elsayed G. Vasan A. R. Mahmood OffRL 42 4 0 18 Oct 2024
MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL C. Voelcker Marcel Hussing Eric Eaton Amir-massoud Farahmand Igor Gilitschenski 39 1 0 11 Oct 2024
Neuroplastic Expansion in Deep Reinforcement Learning Jiashun Liu J. Obando-Ceron Aaron C. Courville L. Pan 39 3 0 10 Oct 2024
Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL Ghada Sokar J. Obando-Ceron Aaron C. Courville Hugo Larochelle Pablo Samuel Castro MoE 124 2 0 02 Oct 2024
The Role of Deep Learning Regularizations on Actors in Offline RL Denis Tarasov Anja Surina Çağlar Gülçehre OffRL AI4CE 50 1 0 11 Sep 2024
Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn Hongyao Tang Glen Berseth OffRL 40 1 0 07 Sep 2024
Can Learned Optimization Make Reinforcement Learning Less Difficult? Alexander David Goldie Chris Xiaoxuan Lu Matthew Jackson Shimon Whiteson Jakob N. Foerster 42 3 0 09 Jul 2024
Normalization and effective learning rates in reinforcement learning Clare Lyle Zeyu Zheng Khimya Khetarpal James Martens H. V. Hasselt Razvan Pascanu Will Dabney 19 7 0 01 Jul 2024
Weight Clipping for Deep Continual and Reinforcement Learning Mohamed Elsayed Qingfeng Lan Clare Lyle A. Rupam Mahmood 29 9 0 01 Jul 2024
Mixture of Experts in a Mixture of RL settings Timon Willi J. Obando-Ceron Jakob Foerster Karolina Dziugaite Pablo Samuel Castro MoE 41 7 0 26 Jun 2024
When does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learning C. Voelcker Tyler Kastner Igor Gilitschenski Amir-massoud Farahmand SSL 34 2 0 25 Jun 2024
Learning Continually by Spectral Regularization Alex Lewandowski Saurabh Kumar Dale Schuurmans András Gyorgy Marlos C. Machado CLL 43 5 0 10 Jun 2024
Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning? Denis Tarasov Kirill Brilliantov Dmitrii Kharlapenko OffRL 32 2 0 10 Jun 2024
A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning Arthur Juliani Jordan T. Ash OffRL OnRL CLL 47 5 0 29 May 2024
Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning Aneesh Muppidi Zhiyu Zhang Heng Yang 34 4 0 26 May 2024
Value Augmented Sampling for Language Model Alignment and Personalization Seungwook Han Idan Shenfeld Akash Srivastava Yoon Kim Pulkit Agrawal OffRL 34 23 0 10 May 2024
No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO Skander Moalla Andrea Miele Razvan Pascanu Çağlar Gülçehre 26 5 0 01 May 2024
Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation Qiang He Tianyi Zhou Meng Fang S. Maghsudi 29 3 0 19 Apr 2024
Can We Understand Plasticity Through Neural Collapse? Guglielmo Bonifazi Iason Chalas Gian Hess Jakub Lucki AI4CE 19 2 0 03 Apr 2024
K-percent Evaluation for Lifelong RL Golnaz Mesbahi Parham Mohammad Panahi Olya Mastikhina Martha White Adam White CLL OffRL 26 0 0 02 Apr 2024
Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons Simon Dufort-Labbé P. DÓro Evgenii Nikishin Razvan Pascanu Pierre-Luc Bacon A. Baratin 34 1 0 12 Mar 2024
Dissecting Deep RL with High Update Ratios: Combatting Value Divergence Marcel Hussing C. Voelcker Igor Gilitschenski Amir-massoud Farahmand Eric Eaton 34 3 0 09 Mar 2024
Reset & Distill: A Recipe for Overcoming Negative Transfer in Continual Reinforcement Learning Hongjoon Ahn Jinu Hyeon Youngmin Oh Bosun Hwang Taesup Moon CLL OnRL 29 2 0 08 Mar 2024
Stop Regressing: Training Value Functions via Classification for Scalable Deep RL Jesse Farebrother Jordi Orbay Q. Vuong Adrien Ali Taïga Yevgen Chebotar ... Sergey Levine Pablo Samuel Castro Aleksandra Faust Aviral Kumar Rishabh Agarwal OffRL 56 56 0 06 Mar 2024
Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning Michal Nauman Michal Bortkiewicz Piotr Milo's Tomasz Trzciñski M. Ostaszewski Marek Cygan OffRL 22 17 0 01 Mar 2024
Disentangling the Causes of Plasticity Loss in Neural Networks Clare Lyle Zeyu Zheng Khimya Khetarpal H. V. Hasselt Razvan Pascanu James Martens Will Dabney AI4CE 53 31 0 29 Feb 2024
In value-based deep reinforcement learning, a pruned network is a good network J. Obando-Ceron Aaron C. Courville Pablo Samuel Castro OffRL 36 18 0 19 Feb 2024
Mixtures of Experts Unlock Parameter Scaling for Deep RL J. Obando-Ceron Ghada Sokar Timon Willi Clare Lyle Jesse Farebrother Jakob N. Foerster Gintare Karolina Dziugaite Doina Precup Pablo Samuel Castro 50 29 0 13 Feb 2024
Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases Ziyi Zhang Sen Zhang Yibing Zhan Yong Luo Yonggang Wen Dacheng Tao EGVM 41 8 0 13 Feb 2024
Discovering Temporally-Aware Reinforcement Learning Algorithms Matthew Jackson Chris Xiaoxuan Lu Louis Kirsch R. T. Lange Shimon Whiteson Jakob N. Foerster 19 18 0 08 Feb 2024
Prediction and Control in Continual Reinforcement Learning N. Anand Doina Precup OffRL CLL 27 11 0 18 Dec 2023
Episodic Return Decomposition by Difference of Implicitly Assigned Sub-Trajectory Reward Hao-Chu Lin Hongqiu Wu Jiaji Zhang Yihao Sun Junyin Ye Yang Yu 19 2 0 17 Dec 2023
Directions of Curvature as an Explanation for Loss of Plasticity Alex Lewandowski Haruto Tanaka Dale Schuurmans Marlos C. Machado 11 5 0 30 Nov 2023
DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization Guowei Xu Ruijie Zheng Yongyuan Liang Xiyao Wang Zhecheng Yuan ... Shuzhen Li Yanjie Ze Hal Daumé Furong Huang Huazhe Xu 38 28 0 30 Oct 2023
Mind the Model, Not the Agent: The Primacy Bias in Model-based RL Zhongjian Qiao Jiafei Lyu Xiu Li 16 3 0 23 Oct 2023
One is More: Diverse Perspectives within a Single Network for Efficient DRL Yiqin Tan Ling Pan Longbo Huang OffRL 32 0 0 21 Oct 2023
Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages Guozheng Ma Lu Li Sen Zhang Zixuan Liu Zhen Wang Yixin Chen Li Shen Xueqian Wang Dacheng Tao OffRL 45 15 0 11 Oct 2023