Catastrophic Interference in Reinforcement Learning: A Solution Based on
Context Division and Knowledge Distillation

v1v2 (latest)

Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation

1 September 2021

Bin Liang

ArXiv (abs)PDF HTML Github (4★)

Papers citing "Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation"

12 / 12 papers shown

Title
LiBOG: Lifelong Learning for Black-Box Optimizer Generation Jiyuan Pei Yi Mei Jialin Liu Mengjie Zhang 48 0 0 19 May 2025
Solving Continual Offline RL through Selective Weights Activation on Aligned Spaces Jifeng Hu Sili Huang Li Shen Zhejian Yang Shengchao Hu Shisong Tang Hechang Chen Yi Chang Dacheng Tao Lichao Sun OffRL 87 0 0 21 Oct 2024
CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community Yan Liu Bin Guo Nuo Li Yasan Ding Zhouyangzi Zhang Zhiwen Yu 135 1 0 09 Jul 2024
Cyclical Weight Consolidation: Towards Solving Catastrophic Forgetting in Serial Federated Learning Haoyue Song Jiacheng Wang Liansheng Wang 72 0 0 17 May 2024
Replay-enhanced Continual Reinforcement Learning Tiantian Zhang Kevin Zehua Shen Zichuan Lin Bo Yuan Xueqian Wang Xiu Li Deheng Ye CLL OffRL 76 6 0 20 Nov 2023
Leveraging Knowledge Distillation for Efficient Deep Reinforcement Learning in Resource-Constrained Environments Guanlin Meng 40 1 0 16 Oct 2023
Predictive Experience Replay for Continual Visual Control and Forecasting Wendong Zhang Geng Chen Xiangming Zhu Siyu Gao Yunbo Wang Xiaokang Yang CLL 95 3 0 12 Mar 2023
Matching DNN Compression and Cooperative Training with Resources and Data Availability F. Malandrino G. Giacomo Armin Karamzade Marco Levorato C. Chiasserini 106 9 0 02 Dec 2022
Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization Tiantian Zhang Zichuan Lin Yuxing Wang Deheng Ye Qiang Fu Wei Yang Xueqian Wang Bin Liang Bo Yuan Xiu Li CLL 101 11 0 01 Sep 2022
Beyond Supervised Continual Learning: a Review Benedikt Bagus A. Gepperth Timothée Lesort BDL CLL 83 10 0 30 Aug 2022
A Study of Continual Learning Methods for Q-Learning Benedikt Bagus A. Gepperth CLL OffRL 98 4 0 08 Jun 2022
Towards Continual Reinforcement Learning: A Review and Perspectives Khimya Khetarpal Matthew D Riemer Irina Rish Doina Precup CLL OffRL 142 324 0 25 Dec 2020