Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective

International Conference on Machine Learning (ICML), 2021

11 May 2021

Papers citing "Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective"

46 / 46 papers shown

Title
Pareto Actor-Critic for Communication and Computation Co-Optimization in Non-Cooperative Federated Learning ServicesIEEE Transactions on Mobile Computing (IEEE TMC), 2025 Renxuan Tan Rongpeng Li Xiaoxue Yu Xianfu Chen Xing Xu Zhifeng Zhao 108 1 0 22 Aug 2025
Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning Roger Creus Castanyer J. Obando-Ceron Lu Li Pierre-Luc Bacon Glen Berseth Aaron Courville Pablo Samuel Castro 166 4 0 18 Jun 2025
Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn Hongyao Tang J. Obando-Ceron Pablo Samuel Castro Aaron Courville Glen Berseth 154 3 0 31 May 2025
Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model Moritz A. Zanger Pascal R. van der Vaart Wendelin Bohmer M. Spaan UQCV BDL 962 3 0 14 Mar 2025
Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the WildComputer Vision and Pattern Recognition (CVPR), 2025 Damien Teney Liangze Jiang Florin Gogianu Ehsan Abbasnejad 986 4 0 13 Mar 2025
Hyperspherical Normalization for Scalable Deep Reinforcement Learning Hojoon Lee Youngdo Lee Takuma Seno Donghu Kim Peter Stone Jaegul Choo 398 9 0 21 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
Evidence on the Regularisation Properties of Maximum-Entropy Reinforcement Learning Rémy Hosseinkhan Boucher Onofrio Semeraro L. Mathelin 230 0 0 28 Jan 2025
Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC Tyler Clark Mark Towers Christine Evers Jonathon Hare OffRL 455 4 0 06 Nov 2024
Robustness and Generalization in Quantum Reinforcement Learning via Lipschitz Regularization Nico Meyer Julian Berberich Christopher Mutschler Daniel D. Scherer 193 5 0 28 Oct 2024
SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement LearningInternational Conference on Learning Representations (ICLR), 2024 Hojoon Lee Dongyoon Hwang Donghu Kim Hyunseung Kim Jun Jet Tai K. Subramanian Peter R. Wurman Jaegul Choo Peter Stone Takuma Seno OffRL 367 39 0 13 Oct 2024
Neural Network Plasticity and Loss Sharpness Max Koster Jude Kukla 263 0 0 25 Sep 2024
The Role of Deep Learning Regularizations on Actors in Offline RL Denis Tarasov Anja Surina Çağlar Gülçehre OffRL AI4CE 306 2 0 11 Sep 2024
On the consistency of hyper-parameter selection in value-based deep reinforcement learning J. Obando-Ceron J. G. Araújo Rameswar Panda Pablo Samuel Castro 347 15 0 25 Jun 2024
A Case for Validation Buffer in Pessimistic Actor-Critic Michal Nauman M. Ostaszewski Marek Cygan 202 0 0 01 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 293 40 0 01 Mar 2024
Active search and coverage using point-cloud reinforcement learning Matthias Rosynski Alexandru Pop L. Buşoniu 3DPC 137 1 0 18 Dec 2023
On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics Michal Nauman Marek Cygan 339 5 0 30 Oct 2023
Mind the Model, Not the Agent: The Primacy Bias in Model-based RLEuropean Conference on Artificial Intelligence (ECAI), 2023 Zhongjian Qiao Jiafei Lyu Xiu Li 213 4 0 23 Oct 2023
Small batch deep reinforcement learningNeural Information Processing Systems (NeurIPS), 2023 J. Obando-Ceron Marc G. Bellemare Pablo Samuel Castro VLM 226 25 0 05 Oct 2023
Learning Multi-Agent Communication with Contrastive LearningInternational Conference on Learning Representations (ICLR), 2023 Y. Lo B. Sengupta Jakob N. Foerster Michael Noukhovitch 230 9 0 03 Jul 2023
PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2023 Hojoon Lee Hanseul Cho Hyunseung Kim Daehoon Gwak Joonkee Kim Jaegul Choo Se-Young Yun Chulhee Yun OffRL 304 39 0 19 Jun 2023
ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive AdvantagesInternational Conference on Machine Learning (ICML), 2023 Andrew Jesson Chris Xiaoxuan Lu Gunshi Gupta Angelos Filos Jakob N. Foerster Y. Gal OffRL 307 9 0 02 Jun 2023
Normalization Enhances Generalization in Visual Reinforcement LearningAdaptive Agents and Multi-Agent Systems (AAMAS), 2023 Lu Li Jiafei Lyu Guozheng Ma Zilin Wang Zhen Yang Xiu Li Zhiheng Li OOD 193 12 0 01 Jun 2023
Deep Reinforcement Learning with Plasticity InjectionNeural Information Processing Systems (NeurIPS), 2023 Evgenii Nikishin Junhyuk Oh Georg Ostrovski Clare Lyle Razvan Pascanu Will Dabney André Barreto OffRL 202 63 0 24 May 2023
Efficient Deep Reinforcement Learning Requires Regulating OverfittingInternational Conference on Learning Representations (ICLR), 2023 Qiyang Li Aviral Kumar Ilya Kostrikov Sergey Levine OffRL 260 42 0 20 Apr 2023
Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2023 Sotetsu Koyamada Shinri Okano Soichiro Nishimori Y. Murata Keigo Habara Haruka Kita Shin Ishii 282 42 0 29 Mar 2023
Understanding plasticity in neural networksInternational Conference on Machine Learning (ICML), 2023 Clare Lyle Zeyu Zheng Evgenii Nikishin Bernardo Avila-Pires Razvan Pascanu Will Dabney AI4CE 434 134 0 02 Mar 2023
The Ladder in Chaos: A Simple and Effective Improvement to General DRL Algorithms by Policy Path Trimming and Boosting Hongyao Tang Hao Fei Jianye Hao 196 2 0 02 Mar 2023
Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value FunctionInternational Conference on Learning Representations (ICLR), 2023 Ruijie Zheng Xiyao Wang Huazhe Xu Furong Huang 202 17 0 02 Feb 2023
Effects of Spectral Normalization in Multi-agent Reinforcement LearningIEEE International Joint Conference on Neural Network (IJCNN), 2022 K. Mehta Anuj Mahajan Kiran Ravish 205 11 0 10 Dec 2022
Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation Chengqian Gao Kelvin Xu Liu Liu Deheng Ye P. Zhao Zhiqiang Xu OffRL 139 2 0 19 Oct 2022
Hyperbolic Deep Reinforcement LearningInternational Conference on Learning Representations (ICLR), 2022 Edoardo Cetin B. Chamberlain Michael M. Bronstein Jonathan J. Hunt 175 24 0 04 Oct 2022
Why neural networks find simple solutions: the many regularizers of geometric complexityNeural Information Processing Systems (NeurIPS), 2022 Benoit Dherin Michael Munn M. Rosca David Barrett 280 42 0 27 Sep 2022
Stabilizing Off-Policy Deep Reinforcement Learning from PixelsInternational Conference on Machine Learning (ICML), 2022 Edoardo Cetin Philip J. Ball Steve Roberts Oya Celiktutan 202 39 0 03 Jul 2022
Exact Spectral Norm Regularization for Neural Networks Anton Johansson Claes Strannegård Niklas Engsner P. Mostad AAML 131 3 0 27 Jun 2022
RORL: Robust Offline Reinforcement Learning via Conservative SmoothingNeural Information Processing Systems (NeurIPS), 2022 Rui Yang Chenjia Bai Xiaoteng Ma Zhaoran Wang Chongjie Zhang Lei Han OffRL 350 101 0 06 Jun 2022
Understanding and Preventing Capacity Loss in Reinforcement LearningInternational Conference on Learning Representations (ICLR), 2022 Clare Lyle Mark Rowland Will Dabney CLL 195 136 0 20 Apr 2022
Learning to Ground Decentralized Multi-Agent Communication with Contrastive Learning Y. Lo B. Sengupta 134 5 0 07 Mar 2022
Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement LearningInternational Conference on Learning Representations (ICLR), 2022 Chenjia Bai Lingxiao Wang Zhuoran Yang Zhihong Deng Animesh Garg Peng Liu Zhaoran Wang OffRL 214 154 0 23 Feb 2022
Functional Regularization for Reinforcement Learning via Learned Fourier FeaturesNeural Information Processing Systems (NeurIPS), 2021 Alexander C. Li Deepak Pathak 191 22 0 06 Dec 2021
Maximum Entropy Model-based Reinforcement Learning Oleg Svidchenko A. Shpilman 124 6 0 02 Dec 2021
Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari Dominik Schmidt Thomas Schmied OffRL 126 15 0 19 Nov 2021
Is High Variance Unavoidable in RL? A Case Study in Continuous ControlInternational Conference on Learning Representations (ICLR), 2021 Johan Bjorck Daniel Schwalbe-Koda Kilian Q. Weinberger 147 30 0 21 Oct 2021
Towards Deeper Deep Reinforcement Learning with Spectral NormalizationNeural Information Processing Systems (NeurIPS), 2021 Johan Bjorck Daniel Schwalbe-Koda Kilian Q. Weinberger 228 25 0 02 Jun 2021
Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness Jeremiah Zhe Liu Zi Lin Shreyas Padhy Dustin Tran Tania Bedrax-Weiss Balaji Lakshminarayanan UQCV BDL 743 513 0 17 Jun 2020