{"id":58029,"url":"https://github.com/schatty/awesome-memory-rl","name":"awesome-memory-rl","description":"A curated list of awesome memory in reinforcement learning research materials","projects_count":72,"last_synced_at":"2026-08-04T12:00:20.638Z","repository":{"id":100478351,"uuid":"403384994","full_name":"schatty/awesome-memory-rl","owner":"schatty","description":"A curated list of awesome memory in reinforcement learning research materials","archived":false,"fork":false,"pushed_at":"2021-09-05T18:33:39.000Z","size":7,"stargazers_count":24,"open_issues_count":0,"forks_count":3,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-07-16T07:04:54.798Z","etag":null,"topics":["awesome-list","deep-learning","memory","memory-deep-learning","memory-mechanisms","memory-reinfocement-learning","memory-rl","reinforcement-learning"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/schatty.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2021-09-05T18:33:22.000Z","updated_at":"2026-05-06T09:16:52.000Z","dependencies_parsed_at":"2023-05-15T02:45:46.073Z","dependency_job_id":null,"html_url":"https://github.com/schatty/awesome-memory-rl","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/schatty/awesome-memory-rl","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/schatty%2Fawesome-memory-rl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/schatty%2Fawesome-memory-rl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/schatty%2Fawesome-memory-rl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/schatty%2Fawesome-memory-rl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/schatty","download_url":"https://codeload.github.com/schatty/awesome-memory-rl/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/schatty%2Fawesome-memory-rl/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":36274788,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-07-20T02:08:10.276Z","status":"online","status_checked_at":"2026-08-04T02:00:06.901Z","response_time":57,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2024-04-08T00:00:26.806Z","updated_at":"2026-08-04T12:00:20.638Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["Reinforcement Learning","Deep Learning","Cognition and Neuroscience"],"sub_categories":["2017","2019","2018","... - 2016","2021","2020"],"readme":"# Awesome Memory in RL\n\n[![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome#readme)\n\n\nA curated list of conference papers studying memory mechanisms for reinforcement learning. Also check [awesome-offline-rl](https://github.com/hanjuku-kaso/awesome-offline-rl), [awesome-ebm](https://github.com/yataobian/awesome-ebm), [awesome-model-mbrl](https://github.com/hejia-zhang/awesome-model-based-reinforcement-learning). Forks and PRs are welcome.\n\n\n## Reinforcement Learning\n### 2021\n* [End-to-End Egospheric Spatial Memory](https://arxiv.org/abs/2102.07764)\n  * Daniel Lenton, Stephen James, Ronald Clark, Andrew J. Davison [ICLR]\n* [Learning Associative Inference Using Fast Weight Memory](https://arxiv.org/abs/2011.07831)\n  * Imanol Schlag, Tsendsuren Munkhdalai, Jürgen Schmidhuber [ICLR]\n* [Solving Continuous Control with Episodic Memory](https://arxiv.org/abs/2106.08832)\n  * Igor Kuznetsov, Andrey Filchenkov [IJCAI]\n* [Generalizable Episodic Memory for Deep Reinforcement Learning](https://arxiv.org/abs/2103.06469)\n  * Hao Hu, Jianing Ye, Guangxiang Zhu, Zhizhou Ren, Chongjie Zhang [ICML]\n### 2020\n* [Episodic Reinforcement Learning with Associative Memory](https://openreview.net/forum?id=HkxjqxBYDB)\n  * Guangxiang Zhu, Zichuan Lin, Guangwen Yang, Chongjie Zhang [ICLR]\n* [AMRL: Aggregated Memory For Reinforcement Learning](https://openreview.net/forum?id=Bkl7bREtDr)\n  * Jacob Beck, Kamil Ciosek, Sam Devlin, Sebastian Tschiatschek, Cheng Zhang, Katja Hofmann [ICLR]\n* [Sparse Graphical Memory for Robust Planning](https://arxiv.org/abs/2003.06417)\n  * Scott Emmons, Ajay Jain, Michael Laskin, Thanard Kurutach, Pieter Abbeel, Deepak Pathak [NeurIPS]\n* [Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards](https://arxiv.org/abs/1907.10247)\n  * Yijie Guo, Jongwook Choi, Marcin Moczulski, Shengyu Feng, Samy Bengio, Mohammad Norouzi, Honglak Lee [NeurIPS]\n* [Working Memory Graphs](https://arxiv.org/abs/1911.07141)\n  * Ricky Loynd, Roland Fernandez, Asli Celikyilmaz, Adith Swaminathan, Matthew Hausknecht [ICML]\n* [Hallucinative Topological Memory for Zero-Shot Visual Planning](https://arxiv.org/abs/2002.12336)\n  * Kara Liu, Thanard Kurutach, Christine Tung, Pieter Abbeel, Aviv Tamar [ICML]\n### 2019\n* [Episodic Curiosity through Reachability](https://arxiv.org/abs/1810.02274)\n  * Nikolay Savinov, Anton Raichuk, Raphaël Marinier, Damien Vincent, Marc Pollefeys, Timothy Lillicrap, Sylvain Gelly [ICLR]\n* [Generalization of Reinforcement Learners with Working and Episodic Memory](https://arxiv.org/abs/1910.13406)\n  * Meire Fortunato, Melissa Tan, Ryan Faulknel et. al [NeurIPS]\n* [Policy Consolidation for Continual Reinforcement Learning](https://arxiv.org/abs/1902.00255)\n  * Christos Kaplanis, Murray Shanahan, Claudia Clopath [ICML]\n* [Remember and Forget for Experience Replay](https://arxiv.org/abs/1807.05827)\n  * Guido Novati, Petros Koumoutsakos [ICML]\n* [Reinforcement Learning, Fast and Slow](https://www.cell.com/trends/cognitive-sciences/fulltext/S1364-6613(19)30061-0)\n  * Matthew Botvinick, Sam Ritter, Jane X. Wang, Zeb Kurth-Nelson, Charles Blundell et. al [Trends in Cognitive Sciences]\n\n### 2018\n* [Memory Augmented Control Networks](https://arxiv.org/abs/1709.05706)\n  * Arbaaz Khan, Clark Zhang, Nikolay Atanasov, Konstantinos Karydis, Vijay Kumar, Daniel D. Lee [ICLR]\n* [Neural Map: Structured Memory for Deep Reinforcement Learning](https://arxiv.org/abs/1702.08360)\n  * Emilio Parisotto, Ruslan Salakhutdinov [ICLR]\n* [Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing](https://arxiv.org/abs/1807.02322)\n  * Chen Liang, Mohammad Norouzi, Jonathan Berant, Quoc Le, Ni Lao [NeurIPS]\n* [Fast deep reinforcement learning using online adjustments from the past](https://arxiv.org/abs/1810.08163)\n  * Steven Hansen, Pablo Sprechmann, Alexander Pritzel, André Barreto, Charles Blundell [NeurIPS]\n* [Continual Reinforcement Learning with Complex Synapses](https://arxiv.org/abs/1802.07239)\n  * Christos Kaplanis, Murray Shanahan, Claudia Clopath [ICML]\n* [Been There, Done That: Meta-Learning with Episodic Recall](https://arxiv.org/abs/1805.09692)\n  * Samuel Ritter, Jane X. Wang, Zeb Kurth-Nelson, Siddhant M. Jayakumar, Charles Blundell et. al [ICML]\n* [Episodic Memory Deep Q-Networks](https://arxiv.org/abs/1805.07603)\n  * Zichuan Lin, Tianqi Zhao, Guangwen Yang, Lintao Zhang [IJCAI]\n* [Unsupervised Predictive Memory in a Goal-Directed Agent ](https://arxiv.org/abs/1803.10760)\n  * Greg Wayne, Chia-Chun Hung, David Amos et. al\n\n### 2017\n* [Fast Reinforcement Learning via Slow Reinforcement Learning](https://arxiv.org/abs/1611.02779)\n  * Yan Duan, John Schulman, Xi Chen, Peter L. Bartlett, Ilya Sutskever, Pieter Abbeel [ICLR]\n* [Neural Episodic Control](https://arxiv.org/abs/1703.01988)\n  * Alexander Pritzel, Benigno Uria, Sriram Srinivasan, Adrià Puigdomènech, Oriol Vinyals, Demis Hassabil et. al [ICML]\n\n\n### ... - 2016\n* [Using Fast Weights to Attend to the Recent Past](https://arxiv.org/abs/1610.06258)\n  * Jimmy Ba, Geoffrey Hinton, Volodymyr Mnih, Joel Z. Leibo, Catalin Ionescu [NIPS-2016]\n* [Control of Memory, Active Perception, and Action in Minecraft](https://arxiv.org/abs/1605.09128)\n  * Junhyuk Oh, Valliappa Chockalingam, Satinder Singh, Honglak Lee [ICLR-2016]\n* [Model-Free Episodic Control](https://arxiv.org/abs/1606.04460)\n  * Charles Blundell, Benigno Uria, Alexander Pritzel et. al\n* [Hippocampal Contributions to Control: The Third Way](https://proceedings.neurips.cc/paper/2007/hash/1f4477bad7af3616c1f933a02bfabe4e-Abstract.html)\n  * Máté Lengyel, Peter Dayan [NIPS-2007]\n\n## Deep Learning\n\n### 2021\n* [Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting](https://arxiv.org/abs/2010.01528)\n  * Sayna Ebrahimi, Suzanne Petryk, Akash Gokul, William Gan, Joseph E. Gonzalez, Marcus Rohrbach, Trevor Darrell [ICLR]\n* [Gradient Projection Memory for Continual Learning](https://arxiv.org/abs/2103.09762)\n  * Gobinda Saha, Isha Garg, Kaushik Roy [ICLR]\n* [Learn from Concepts: Towards the Purified Memory for Few-shot Learning](https://www.ijcai.org/proceedings/2021/123)\n  * Xuncheng Liu, Xudong Tian, Shaohui Lin, Yanyun Qu, Lizhuang Ma, Wang Yuan, Zhizhong Zhang, Yuan Xi [IJCAI]\n* [Not All Memories are Created Equal: Learning to Forget by Expiring](https://arxiv.org/abs/2105.06548)\n  * Sainbayar Sukhbaatar, Da Ju, Spencer Poff, Stephen Roller, Arthur Szlam, Jason Weston, Angela Fan [ICML]\n\n### 2020\n* [Memory-Based Graph Networks](https://arxiv.org/abs/2002.09518)\n  * Amir Hosein Khasahmadi, Kaveh Hassani, Parsa Moradi, Leo Lee, Quaid Morris [ICLR]\n* [Meta-Learning Deep Energy-Based Memory Models](https://arxiv.org/abs/1910.02720)\n  * Sergey Bartunov, Jack W Rae, Simon Osindero, Timothy P Lillicrap [ICLR]\n* [MEMO: A Deep Network for Flexible Combination of Episodic Memories](https://arxiv.org/abs/2001.10913)\n  * Andrea Banino, Adrià Puigdomènech Badia, Raphael Köster et. al [ICLR]\n* [Progressive Memory Banks for Incremental Domain Adaptation](https://arxiv.org/abs/1811.00239)\n  * Nabiha Asghar, Lili Mou, Kira A. Selby, Kevin D. Pantasdo, Pascal Poupart, Xin Jiang [ICLR]\n* [Neural Stored-program Memory](https://arxiv.org/abs/1906.08862)\n  * Hung Le, Truyen Tran, Svetha Venkatesh [ICLR]\n* [H-Mem: Harnessing synaptic plasticity with Hebbian Memory Networks](https://proceedings.neurips.cc/paper/2020/file/f6876a9f998f6472cc26708e27444456-Paper.pdf)\n  * Thomas Limbacher and Robert Legenstein [NeurIPS]\n* [Online Multitask Learning with Long-Term Memory](https://arxiv.org/abs/2008.07055)\n  * Mark Herbster, Stephen Pasteris, Lisa Tse [NeurIPS]\n* [HiPPO: Recurrent Memory with Optimal Polynomial Projections](https://arxiv.org/abs/2008.07669)\n  * Albert Gu, Tri Dao, Stefano Ermon, Atri Rudra, Christopher Re [NeurIPS]\n* [Learning to Learn Variational Semantic Memory](https://arxiv.org/abs/2010.10341)\n  * Xiantong Zhen, Yingjun Du, Huan Xiong, Qiang Qiu, Cees G. M. Snoek, Ling Shao [NeurIPS]\n* [Improved Schemes for Episodic Memory-based Lifelong Learning](https://arxiv.org/abs/1909.11763)\n  * Yunhui Guo, Mingrui Liu, Tianbao Yang, Tajana Rosing [NeurIPS]\n* [Self-Attentive Associative Memory](https://arxiv.org/abs/2002.03519)\n  * Hung Le, Truyen Tran, Svetha Venkatesh [ICML]\n* [Associative Memory in Iterated Overparameterized Sigmoid Autoencoders](https://arxiv.org/abs/2006.16540)\n  * Yibo Jiang, Cengiz Pehlevan [ICML]\n* [Multigrid Neural Memory](https://arxiv.org/abs/1906.05948)\n  * Tri Huynh, Michael Maire, Matthew R. Walter [ICML]\n\n### 2019\n\n* [Learning to Remember More with Less Memorization](https://arxiv.org/abs/1901.01347)\n  * Hung Le, Truyen Tran, Svetha Venkatesh [ICLR]\n* [Adaptive Posterior Learning: few-shot learning with a surprise-based memory module](https://arxiv.org/abs/1902.02527)\n  * Tiago Ramalho, Marta Garnelo [ICLR]\n* [Large Memory Layers with Product Keys](https://arxiv.org/abs/1907.05242)\n  * Guillaume Lample, Alexandre Sablayrolles, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou [NeurIPS]\n* [Episodic Memory in Lifelong Language Learning](https://arxiv.org/abs/1906.01076)\n  * Cyprien de Masson d'Autume, Sebastian Ruder, Lingpeng Kong, Dani Yogatama [NeurIPS]\n* [Metalearned Neural Memory](https://arxiv.org/abs/1907.09720)\n  * Tsendsuren Munkhdalai, Alessandro Sordoni, Tong Wang, Adam Trischler [NeurIPS]\n* [Ordered Memory](https://arxiv.org/abs/1910.13466)\n  * Yikang Shen, Shawn Tan, Arian Hosseini, Zhouhan Lin, Alessandro Sordoni, Aaron Courville [NeurIPS]\n* [Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks](https://papers.nips.cc/paper/2019/file/952285b9b7e7a1be5aa7849f32ffff05-Paper.pdf)\n  * Aaron R. Voelker, Ivana Kajic ́, Chris Eliasmith [NeurIPS]\n\n### 2018\n\n* [Semi-parametric Topological Memory for Navigation](https://arxiv.org/abs/1803.00653)\n  * Nikolay Savinov, Alexey Dosovitskiy, Vladlen Koltun [ICLR]\n* [Memory-based Parameter Adaptation](https://arxiv.org/abs/1802.10542)\n  * Pablo Sprechmann, Siddhant M. Jayakumar, Jack W. Rae, Alexander Pritzel et. al [ICLR]\n* [Convolutional Memory Blocks for Depth Data Representation Learning](https://www.ijcai.org/proceedings/2018/0387.pdf)\n  * Keze Wang, Liang Lin, Chuangjie Ren, Wei Zhang, Wenxiu Sun [IJCAI]\n* [Visual Memory for Robust Path Following](https://arxiv.org/abs/1812.00940)\n  * Ashish Kumar, Saurabh Gupta, David Fouhey, Sergey Levine, Jitendra Malik [NeurIPS]\n* [A Simple Cache Model for Image Recognition](https://arxiv.org/abs/1805.08709)\n  * A. Emin Orhan [NeurIPS]\n* [Variational Memory Encoder-Decoder](https://arxiv.org/abs/1807.09950)\n  * Hung Le, Truyen Tran, Thin Nguyen, Svetha Venkatesh [NeurIPS]\n* [Fast Parametric Learning with Activation Memorization](https://arxiv.org/abs/1803.10049)\n  * Jack W Rae, Chris Dyer, Peter Dayan, Timothy P Lillicrap [ICML]\n* [Learning and Memorization](http://proceedings.mlr.press/v80/chatterjee18a.html)\n  * Satrajit Chatterjee [ICML]\n\n### 2017\n\n* [Reasoning with Memory Augmented Neural Networks for Language Comprehension](https://arxiv.org/abs/1610.06454)\n  * Tsendsuren Munkhdalai, Hong Yu [ICLR]\n* [Learning to Remember Rare Events](https://arxiv.org/abs/1703.03129)\n  * Łukasz Kaiser, Ofir Nachum, Aurko Roy, Samy Bengio [ICLR]\n* [Variational Memory Addressing in Generative Models](https://arxiv.org/abs/1709.07116)\n  * Jörg Bornschein, Andriy Mnih, Daniel Zoran, Danilo J. Rezende [NIPS]\n* [A simple model of recognition and recall memory](https://papers.nips.cc/paper/2017/hash/57aeee35c98205091e18d1140e9f38cf-Abstract.html)\n  * Nisheeth Srivastava, Edward Vul [NIPS]\n* [Gradient Episodic Memory for Continual Learning](https://arxiv.org/abs/1706.08840)\n  * David Lopez-Paz, Marc'Aurelio Ranzato [NIPS]\n\n### ... - 2016\n\n* [End-To-End Memory Networks](https://arxiv.org/abs/1503.08895) [NIPS-205]\n\n## Cognition and Neuroscience\n\n* [Large Associative Memory Problem in Neurobiology and Machine Learning](https://arxiv.org/abs/2008.06996)\n  * Dmitry Krotov, John Hopfield [ICLR-2021]\n* [Compositional Explanations of Neurons](https://arxiv.org/abs/2006.14032)\n  * Jesse Mu, Jacob Andreas [NeurIPS-2020]\n* [Coordinated hippocampal-entorhinal replay as structural inference](https://proceedings.neurips.cc/paper/2019/hash/aa68c75c4a77c87f97fb686b2f068676-Abstract.html)\n  * Talfan Evans, Neil Burgess [NeurIPS-2019]\n* [Generalisation of structural knowledge in the hippocampal-entorhinal system](https://arxiv.org/abs/1805.09042)\n  * James C. R. Whittington, Timothy H. Muller, Shirley Mark, Caswell Barry, Timothy E. J. Behrens [NeurIPS-2018]\n* [Dendritic cortical microcircuits approximate the backpropagation algorithm](https://arxiv.org/abs/1810.11393)\n  * João Sacramento, Rui Ponte Costa, Yoshua Bengio, Walter Senn [NeurIPS-2018]\n\n\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/schatty%2Fawesome-memory-rl/projects"}