├── 01_Examples.png ├── CONTRIBUTING.md ├── LICENSE └── README.md /01_Examples.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/familyld/Awesome-Causal-RL/HEAD/01_Examples.png -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- 1 | # Contributing to Awesome Causal Reinforcement Learning 2 | 3 | Anyone interested in Causal Reinforcement Learning is welcomed to contribute to this repo: 4 | 5 | - You can add classical or latest publications / tutorials directly to `README.md`. 6 | 7 | - You are welcomed to update anything helpful. 8 | 9 | 10 | ## Pull Requests 11 | 12 | In general, we follow the "fork-and-pull" Git workflow. 13 | 14 | 1. Fork this repo on your personal GitHub. 15 | 16 | 2. Clone this repo to your own machine. 17 | ``` 18 | git clone https://github.com//Awesome-Causal-RL.git 19 | ``` 20 | 21 | 3. Make necessary changes and commit those changes. 22 | 23 | - If you go to this project directory and execute the command `git status`, you'll see there are changes. 24 | 25 | - Add those changes to the branch using the `git add` command: 26 | ``` 27 | git add 28 | ``` 29 | - Now commit those changes using the `git commit` command: 30 | ``` 31 | git commit -m "add(): commit message" 32 | ``` 33 | * `Template`: add/feature/polish(your_name): commit message 34 | * `Example`: add(张三): add one paper about CausalRL on #neurips2022 35 | 36 | 37 | 1. Push your work back up to your fork. 38 | ``` 39 | git push origin 40 | ``` 41 | 42 | 2. Submit a Pull request so that we can review your changes. 43 | 44 | - If you go to your repository on GitHub, you'll see a `Contribute` button. Click on that button. Then click `Open pull request` and `Create pull request` buttons in turn. 45 | 46 | - Soon We will be merging all your changes into the main branch of this repo. You will get a notification email once the changes have been merged. 47 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Awesome Causal Reinforcement Learning 2 | ![Awesome](https://awesome.re/badge.svg) ![GitHub stars](https://img.shields.io/github/stars/familyld/Awesome-Causal-RL?color=yellow) ![GitHub forks](https://img.shields.io/github/forks/familyld/Awesome-Causal-RL?color=9cf) ![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg) 3 | 4 | The goal of this repository is to provide a curated list of resources in **Causal Reinforcement Learning (RL)**. If you have any suggestions (missing papers, tutorials, typos, or amazing blog posts), please feel free to edit and pull a request. If you find this repo helpful, please give us a star ⭐. 5 | 6 | For people who are new to this field, we strongly recommend you to read our comprehensive survey published on TMLR (2023): [Causal Reinforcement Learning: A Survey](https://openreview.net/pdf?id=qqnttX9LPo) as a starting point. You may also find the [slides](https://2wildkids.com/talks/2023-08-21-ADMA_tutorial) of our tutorial at ADMA 2023 helpful 😉. 7 | 8 | ## Table of Contents 9 | 10 | - [Awesome Causal Reinforcement Learning](#awesome-causal-reinforcement-learning) 11 | - [Table of Contents](#table-of-contents) 12 | - [A Brief Overview](#a-brief-overview) 13 | - [Talks](#talks) 14 | - [Papers](#papers) 15 | - [2023](#2023) 16 | - [2022](#2022) 17 | - [2021](#2021) 18 | - [2020](#2020) 19 | - [2019 and before](#2019-and-before) 20 | - [Environments](#environments) 21 | - [Others](#others) 22 | - [Contributing](#contributing) 23 | - [License](#license) 24 | 25 | ## A Brief Overview 26 | 27 | ![](01_Examples.png) 28 | 29 | In practical reinforcement learning applications, understanding causality is of great significance. Take a peek at the real-life scenarios shown in the above figure: 30 | 31 | - Imagine you're teaching a robot agent to grab things. Seems straightforward, right? But it's not just about what the robot does; it's about figureing out why certain actions can lead to the expected outcomes. If a factor changes, how does it affect the result? 32 | - Now, let's think about an agent trying to determine the treatment in medical scenarios. While it can access a patient's medical history, hidden factors sometimes mess things up. Maybe the socioeconomic status affects how the patients respond to treatments, and such info is missing in the records. How can the agent make the best decision under such unobserved confounders? 33 | - Then there's autonomous driving. To ensure safety, agents must learn from both past experiences and hypothetical scenarios where they took different actions. For instance, would a crash have occurred if the vehicle hadn't slowed down? Here, counterfactual thinking aids in safer driving. 34 | 35 | In all these cases, causality plays a key role in decision-making, yet teaching agents to think causally is not a walk in the park. In recent years, researchers have been actively exploring systematic approaches to integrate causality into the realm of reinforcement learning, giving rise to an emerging field known as causal RL: 36 | 37 | > Causal RL is an umbrella term for RL approaches that incorporate additional assumptions or prior knowledge to analyze and understand the causal mechanisms underlying actions and their consequences, enabling agents to make more informed and effective decisions. 38 | 39 | This definition emphasizes two fundamental aspects that distinguish causal RL from non-causal RL. 1) It emphasizes a focus on causality, seeking to advance beyond superficial associations or data patterns. To meet this goal, 2) it necessitates the incorporation of additional assumptions or knowledge that accounts for the causal relationships inherent in decision-making problems. 40 | 41 | ## Talks 42 | 43 | ``` 44 | format: 45 | - [title](link) [other links] 46 | - author1, author2, and author3... 47 | - conference or activity 48 | ``` 49 | 50 | - 【Tutorial】[Towards Causal Reinforcement Learning](http://auai.org/uai2019/tutorials.php#tutorial3) [[Video](https://www.youtube.com/watch?v=-cfXn3vopyw)] 51 | - Elias Bareinboim 52 | - The Conference on Uncertainty in Artificial Intelligence (UAI) 2019 53 | - [Causal Reinforcement Learning: A Road to Artificial General Intelligence](https://www.youtube.com/watch?v=sqKcbjuXGn8) [[Slides](https://causallu.files.wordpress.com/2019/11/talkbelllabs28nov2019.pdf)] 54 | - Chaochao Lu 55 | - Social Dynamics Seminar, NOKIA Bell Labs, 28 Nov 2019 56 | - 【Tutorial】[Towards Causal Reinforcement Learning](https://crl.causalai.net/) [[Video](https://www.youtube.com/watch?v=QRTgLWfFBMM)] 57 | - Elias Bareinboim 58 | - The International Conference on Machine Learning (ICML) 2020 59 | - [Causal Reinforcement Learning: Motivation, Concepts, Challenges, and Applications](https://campus.swarma.org/course/2156) [[Slides](https://causallu.files.wordpress.com/2020/11/talkswarmacampus29nov2020.pdf)] 60 | - Chaochao Lu 61 | - Causal Science and Causal AI Reading Group, Swarma Campus, 29 Nov 2020 62 | - [Towards Causal Representation Learning](https://www.youtube.com/watch?v=rKZJ0TJWvTk) [[Slides](https://www.bradyneal.com/slides/Yoshua_Bengio_Guest_Talk_Towards_Causal_Representation_Learning.pdf)] 63 | - Yoshua Bengio 64 | - Mila Causality Inference Lectures, 30 Nov 2020 65 | - [A Survey on Causal Reinforcement Learning](https://pattern.swarma.org/study_group_issue/414) [[Paper](https://arxiv.org/pdf/2302.05209.pdf)] 66 | - Yan Zeng 67 | - Causal Science and Causal AI Reading Group, Swarma Campus, 12 Mar 2023 68 | - 【Tutorial】[Causal Reinforcement Learning: Empowering Agents with Causality](https://adma2023.uqcloud.net/tutorial.html) [[Slides](https://2wildkids.com/talks/2023-08-21-ADMA_tutorial)] 69 | - Zhihong Deng, Jing Jiang 70 | - The International Conference on Advanced Data Mining and Applications (ADMA) 2023 71 | 72 | 73 | ## Papers 74 | 75 | ``` 76 | format: 77 | - [title](paper link) [other links] 78 | - author1, author2, and author3... 79 | - keyword 80 | - code 81 | ``` 82 | 83 | ### 2023 84 | - 【Survey】[Causal Reinforcement Learning: A Survey](https://arxiv.org/abs/2307.01452) 85 | - Zhihong Deng, Jing Jiang, Guodong Long, Chengqi Zhang 86 | - 【Survey】[A Survey on Causal Reinforcement Learning](https://arxiv.org/abs/2302.05209) 87 | - Yan Zeng, Ruichu Cai, Fuchun Sun, Libo Huang, Zhifeng Hao 88 | - [Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach](https://openreview.net/forum?id=w7TyuWhGZP) 89 | - Yudi Zhang, Yali Du, Biwei Huang, Ziyan Wang, Jun Wang, Meng Fang, Mykola Pechenizkiy 90 | - Code: [Github Repository](https://github.com/ReedZyd/GenerativeReturnDecomposition) 91 | - [False Correlation Reduction for Offline Reinforcement Learning](https://ieeexplore.ieee.org/document/10301548) [[Blog Post](https://familyld.github.io/posts/2023/11/SCORE/)] 92 | - Zhihong Deng, Zuyue Fu, Lingxiao Wang, Zhuoran Yang, Chenjia Bai, Tianyi Zhou, Zhaoran Wang, Jing Jiang 93 | - Code: [Github Repository](https://github.com/familyld/SCORE) 94 | - [CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender System](https://dl.acm.org/doi/abs/10.1145/3594871) 95 | - Chongming Gao, Shiqi Wang, Shijun Li, Jiawei Chen, Xiangnan He, Wenqiang Lei, Biao Li, Yuan Zhang, Peng Jiang 96 | - Code: [Github Repository](https://github.com/chongminggao/CIRS-codes) 97 | - [Learning World Models with Identifiable Factorization](https://openreview.net/forum?id=6JJq5TW9Mc) 98 | - Yu-Ren Liu, Biwei Huang, Zhengmao Zhu, Honglong Tian, Mingming Gong, Yang Yu, Kun Zhang 99 | - Code: [Github Repository](https://github.com/AlexLiuyuren/Factor) 100 | - [Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning?](https://proceedings.mlr.press/v213/gupta23a.html) 101 | - Gunshi Gupta, Tim G. J. Rudner, Rowan Thomas McAllister, Adrien Gaidon, Yarin Gal 102 | - [Using Confounded Data in Latent Model-Based Reinforcement Learning](https://openreview.net/forum?id=nFWRuJXPkU) 103 | - Maxime Gasse, Damien Grasset, Guillaume Gaudron, Pierre-Yves Oudeyer 104 | - [Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding](https://openreview.net/pdf?id=Jz9I_Mif7mm) 105 | - Alizée Pace, Hugo Yèche, Bernhard Schölkopf, Gunnar Ratsch, Guy Tennenholtz 106 | 107 | 108 | ### 2022 109 | - 【Survey】[Causal Machine Learning: A Survey and Open Problems](https://arxiv.org/abs/2206.15475) [[Website](https://www.causal-machine-learning.com/)] 110 | - Jean Kaddour, Aengus Lynch, Qi Liu, Matt J. Kusner, Ricardo Silva 111 | - [Causal Dynamics Learning for Task-Independent State Abstraction](https://proceedings.mlr.press/v162/wang22ae.html) 112 | - Zizhao Wang, Xuesu Xiao, Zifan Xu, Yuke Zhu, Peter Stone 113 | - Code: [Github Repository](https://github.com/wangzizhao/CausalDynamicsLearning) 114 | - [Invariant Policy Learning: A Causal Perspective](https://dl.acm.org/doi/abs/10.1109/TPAMI.2022.3232363) 115 | - Sorawit Saengkyongam, Nikolaj Thams, Jonas Peters, 116 | Niklas Pfister 117 | - Keyword: Causality, distributional shift, contextual bandits, off-policy learning 118 | - Code: [Github Repository](https://github.com/sorawitj/invariant-policy-learning) 119 | - [Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning](https://papers.nips.cc/paper_files/paper/2022/hash/a96368eb38bce0956a1132154d70d72d-Abstract-Conference.html) 120 | - Wenhao Ding, Haohong Lin, Bo Li, Ding Zhao 121 | - Code: [Github Repository](https://github.com/GilgameshD/GRADER) 122 | - [A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning](https://openreview.net/forum?id=YRq0ZUnzKoZ) 123 | - Jiaxian Guo, Mingming Gong, Dacheng Tao 124 | - Code: [Github Repository](https://github.com/CR-Gjx/RIA) 125 | - [MoCoDA: Model-based Counterfactual Data Augmentation](https://openreview.net/forum?id=w6tBOjPCrIO) 126 | - Silviu Pitis, Elliot Creager, Ajay Mandlekar, Animesh Garg 127 | - Code: [Github Repository](https://github.com/spitis/mocoda) 128 | - [AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning](https://openreview.net/forum?id=8H5bpVwvt5) 129 | - Biwei Huang, Fan Feng, Chaochao Lu, Sara Magliacane, Kun Zhang 130 | - Code: [Github Repository](https://github.com/Adaptive-RL/AdaRL-code) 131 | - [Offline Reinforcement Learning with Causal Structured World Models](https://arxiv.org/pdf/2206.01474) 132 | - Zheng-Mao Zhu, Xiong-Hui Chen, Hong-Long Tian, Kun Zhang, Yang Yu 133 | - [Provably Efficient Offline Reinforcement Learning for Partially Observable Markov Decision Processes](https://proceedings.mlr.press/v162/guo22a.html) 134 | - Hongyi Guo, Qi Cai, Yufeng Zhang, Zhuoran Yang, Zhaoran Wang 135 | - [Training a Resilient Q-network against Observational Interference](https://arxiv.org/pdf/2102.09677.pdf) [[Slides](https://docs.google.com/presentation/d/1WOgnMKszZ6eYwxiR0jLZjrj7XbmKpEf9sNrbI8poSMg/edit?usp=sharing)] 136 | - Chao-Han Huck Yang, I-Te Danny Hung, Yi Ouyang, Pin-Yu Chen 137 | - Code: [Github Repository](https://github.com/huckiyang/Obs-Causal-Q-Network) 138 | - [Online Reinforcement Learning for Mixed Policy Scopes](https://proceedings.neurips.cc/paper_files/paper/2022/hash/15349e1c554406b7719d047a498e7117-Abstract-Conference.html) 139 | - Junzhe Zhang, Elias Bareinboim 140 | - [Action-Sufficient State Representation Learning for Control with Structural Constraints](https://openreview.net/forum?id=HrxfwSu8cl9) 141 | - Biwei Huang, Chaochao Lu, Liu Leqi, José Miguel Hernández-Lobato, Clark Glymour, Bernhard Schölkopf, Kun Zhang 142 | - [Actual Causality and Responsibility Attribution in Decentralized Partially Observable Markov Decision Processes](https://dl.acm.org/doi/10.1145/3514094.3534133) 143 | - Stelios Triantafyllou, Adish Singla, Goran Radanovic 144 | - [Reinforcement Learning of Causal Variables Using Mediation Analysis](https://ojs.aaai.org/index.php/AAAI/article/view/20648) 145 | - Tue Herlau, Rasmus Larsen 146 | - [Achieving Counterfactual Fairness for Causal Bandit](https://ojs.aaai.org/index.php/AAAI/article/view/20653) 147 | - Wen Huang, Lu Zhang, Xintao Wu 148 | - [SCALES: From Fairness Principles to Constrained Decision-Making](https://dl.acm.org/doi/10.1145/3514094.3534190) 149 | - Sreejith Balakrishnan, Jianxin Bi, Harold Soh 150 | 151 | 152 | ### 2021 153 | - 【Survey】[Toward Causal Representation Learning](https://ieeexplore.ieee.org/abstract/document/9363924) [[Video](https://www.youtube.com/watch?v=rKZJ0TJWvTk)] 154 | - Bernhard Schölkopf, Francesco Locatello, Stefan Bauer, Nan Rosemary Ke, Nal Kalchbrenner, Anirudh Goyal, Yoshua Bengio 155 | - [Invariant Causal Imitation Learning for Generalizable Policies](https://proceedings.neurips.cc/paper/2021/hash/204904e461002b28511d5880e1c36a0f-Abstract.html) 156 | - Ioana Bica, Daniel Jarrett, Mihaela van der Schaar 157 | - Code: [Github Repository](https://github.com/ioanabica/Invariant-Causal-Imitation-Learning) 158 | - [Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning](http://proceedings.mlr.press/v139/sontakke21a.html) 159 | - Sumedh A Sontakke, Arash Mehrjou, Laurent Itti, Bernhard Schölkopf 160 | - Code: [Github Repository](https://github.com/sumedh7/CausalCuriosity) 161 | - [Causal Reasoning in Simulation for Structure and Transfer Learning of Robot Manipulation Policies](https://ieeexplore.ieee.org/document/9561439) 162 | - Tabitha E. Lee, Jialiang Alan Zhao, Amrita S. Sawhney, Siddharth Girdhar, Oliver Kroemer 163 | - [CausalDyna: Improving Generalization of Dyna-style Reinforcement Learning via Counterfactual-Based Data Augmentation](https://openreview.net/pdf?id=uy602F8cTrh) 164 | - Deyao Zhu, Li Erran Li, Mohamed Elhoseiny 165 | - [Learning to infer unseen contexts in causal contextual reinforcement learning](https://openreview.net/pdf?id=gPZP5ha9LpX) [[Website](https://eghbalz.github.io/carl/index.html)] 166 | - Hamid Eghbal-zadeh\*, Florian Henkel\*, Gerhard Widmer 167 | - Code: [Github Repository](https://github.com/eghbalz/contextual-gridworld) 168 | - [Sequential Causal Imitation Learning with Unobserved Confounders](https://openreview.net/forum?id=o6-k168bBD8) 169 | - Daniel Kumor, Junzhe Zhang, Elias Bareinboim 170 | - [Causal Imitation Learning under Temporally Correlated Noise](https://arxiv.org/pdf/2202.01312.pdf) [[Website](https://gokul.dev/causil/)] [[Video](https://www.youtube.com/watch?v=FPyL9vMGpFE)] 171 | - Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell, Zhiwei Steven Wu 172 | - Code: [Github Repository](https://github.com/gkswamy98/causal_il) 173 | - [Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders](http://proceedings.mlr.press/v130/bennett21a/bennett21a.pdf) 174 | - Andrew Bennett, Nathan Kallus, Lihong Li, Ali Mousavi 175 | - [Provably Efficient Causal Reinforcement Learning with Confounded Observational Data](https://openreview.net/forum?id=tUeeRzMXJZ) 176 | - Lingxiao Wang, Zhuoran Yang, Zhaoran Wang 177 | - [Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning](https://arxiv.org/abs/2102.09907) 178 | - Luofeng Liao, Zuyue Fu, Zhuoran Yang, Yixin Wang, Mladen Kolar, Zhaoran Wang 179 | - [Addressing Hindsight Bias in Multigoal Reinforcement Learning](https://ieeexplore.ieee.org/document/9531338) 180 | - Chenjia Bai, Lingxiao Wang, Yixin Wang, Zhaoran Wang, Rui Zhao, Chenyao Bai, Peng Liu 181 | - Code: [Github Repository](https://github.com/Baichenjia/BHER) 182 | - Keyword: Hindsight bias, hindsight experience replay (HER), reinforcement learning (RL) 183 | - [Causal Influence Detection for Improving Efficiency in Reinforcement Learning](https://arxiv.org/abs/2106.03443) 184 | - Maximilian Seitzer, Bernhard Schölkopf, Georg Martius 185 | - Code: [Github Repository](https://github.com/martius-lab/cid-in-rl) 186 | - [Learning "What-if" Explanations for Sequential Decision-Making](https://openreview.net/forum?id=h0de3QWtGG) 187 | - Ioana Bica, Daniel Jarrett, Alihan Hüyük, Mihaela van der Schaar 188 | - [Counterfactual Credit Assignment in Model-Free Reinforcement Learning](https://proceedings.mlr.press/v139/mesnard21a.html) 189 | - Thomas Mesnard, Theophane Weber, Fabio Viola, Shantanu Thakoor, Alaa Saade, Anna Harutyunyan, Will Dabney, Thomas S Stepleton, Nicolas Heess, Arthur Guez, Eric Moulines, Marcus Hutter, Lars Buesing, Remi Munos 190 | - [Counterfactual Explanations in Sequential Decision Making Under Uncertainty](https://openreview.net/forum?id=M5h1l1SldlF) 191 | - Stratis Tsirtsis, Abir De, Manuel Gomez Rodriguez 192 | - Code: [Github Repository](https://github.com/Networks-Learning/counterfactual-explanations-mdp) 193 | - [Reward tampering problems and solutions in reinforcement learning: A causal influence diagram perspective](https://arxiv.org/abs/1908.04734) 194 | - Tom Everitt, Marcus Hutter, Ramana Kumar, Victoria Krakovna 195 | 196 | 197 | ### 2020 198 | - [Invariant Causal Prediction for Block MDPs](http://proceedings.mlr.press/v119/zhang20t.html) 199 | - Amy Zhang, Clare Lyle, Shagun Sodhani, Angelos Filos, Marta Kwiatkowska, Joelle Pineau, Yarin Gal, Doina Precup 200 | - Code: [Github Repository](https://github.com/facebookresearch/icp-block-mdp) 201 | - [Causal imitation learning with unobserved confounders](https://dl.acm.org/doi/10.5555/3495724.3496752) 202 | - Junzhe Zhang, Daniel Kumor, Elias Bareinboim 203 | - [Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding](https://paperswithcode.com/paper/off-policy-policy-evaluation-for-sequential) 204 | - Hongseok Namkoong, Ramtin Keramati, Steve Yadlowsky, Emma Brunskill 205 | - Code: [Github Repository](https://github.com/StanfordAI4HI/off_policy_confounding) 206 | - [Causally Correct Partial Models for Reinforcement Learning](https://arxiv.org/abs/2002.02836) 207 | - Danilo J. Rezende, Ivo Danihelka, George Papamakarios, Nan Rosemary Ke, Ray Jiang, Theophane Weber, Karol Gregor, Hamza Merzic, Fabio Viola, Jane Wang, Jovana Mitrovic, Frederic Besse, Ioannis Antonoglou, Lars Buesing 208 | - [Designing Optimal Dynamic Treatment Regimes: A Causal Reinforcement Learning Approach](https://proceedings.mlr.press/v119/zhang20a.html) 209 | - Junzhe Zhang, Elias Bareinboim 210 | - [Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation](https://arxiv.org/abs/2012.09092) 211 | - Chaochao Lu, Biwei Huang, Ke Wang, José Miguel Hernández-Lobato, Kun Zhang, Bernhard Schölkopf 212 | - [Counterfactual Data Augmentation using Locally Factored Dynamics](https://dl.acm.org/doi/10.5555/3495724.3496059) 213 | - Silviu Pitis, Elliot Creager, Animesh Garg 214 | - [Explainable Reinforcement Learning through a Causal Lens](https://ojs.aaai.org/index.php/AAAI/article/view/5631) [[Video](https://www.youtube.com/watch?v=PzzT4nRMhmM)] 215 | - Prashan Madumal, Tim Miller, Liz Sonenberg, Frank Vetere 216 | - [Counterfactual Policy Evaluation for Decision-Making in Autonomous Driving](https://arxiv.org/abs/2003.11919) 217 | - Patrick Hart, Alois Knoll 218 | - Code: [Github Repository](https://github.com/bark-simulator/bark) 219 | 220 | 221 | ### 2019 and before 222 | - [Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search](https://openreview.net/forum?id=BJG0voC9YQ) 223 | - Lars Buesing, Theophane Weber, Yori Zwols, Nicolas Heess, Sebastien Racaniere, Arthur Guez, Jean-Baptiste Lespiau 224 | - [Near-Optimal Reinforcement Learning in Dynamic Treatment Regimes](https://proceedings.neurips.cc/paper/2019/hash/8252831b9fce7a49421e622c14ce0f65-Abstract.html) 225 | - Junzhe Zhang, Elias Bareinboim 226 | - [Causal Induction from Visual Observations for Goal Directed Tasks](https://arxiv.org/pdf/1910.01751.pdf) 227 | - Suraj Nair, Yuke Zhu, Silvio Savarese, Li Fei-Fei 228 | - Code: [Github Repository](https://github.com/StanfordVL/causal_induction) 229 | - [Causal Reasoning from Meta-reinforcement learning](https://openreview.net/forum?id=H1ltQ3R9KQ) 230 | - Ishita Dasgupta, Jane Wang, Silvia Chiappa, Jovana Mitrovic, Pedro Ortega, David Raposo, Edward Hughes, Peter Battaglia, Matthew Botvinick, Zeb Kurth-Nelson 231 | - Code: [Github Repository](https://github.com/threewisemonkeys-as/causal-meta-rl) 232 | - [Counterfactual multi-agent policy gradients](https://dl.acm.org/doi/10.5555/3504035.3504398#d105486545e1) [[Video](https://www.youtube.com/watch?v=3OVvjE5B9LU)] 233 | - Jakob N. Foerster, Gregory Farquhar, Triantafyllos Afouras, Nantas Nardelli, Shimon Whiteson 234 | - Code: [Github Repository](https://github.com/matteokarldonati/Counterfactual-Multi-Agent-Policy-Gradients) 235 | - [Fairness in Decision-Making — The Causal Explanation Formula](https://ojs.aaai.org/index.php/AAAI/article/view/11564) 236 | - Junzhe Zhang, Elias Bareinboim 237 | - [Transfer Learning in Multi-Armed Bandits: A Causal Approach](https://www.ijcai.org/proceedings/2017/186) 238 | - Junzhe Zhang, Elias Bareinboim 239 | - Keyword: Knowledge Representation, Reasoning, and Logic: Action, Change and Causality; Uncertainty in AI: Graphical Models; Uncertainty in AI: Sequential Decision Making 240 | - [Deconfounding Reinforcement Learning in Observational Settings](https://arxiv.org/abs/1812.10576) 241 | - Chaochao Lu, José Miguel Hernández Lobato 242 | - Code: [Github Repository](https://github.com/CausalRL/DRL) 243 | 244 | 245 | 246 | ## Environments 247 | ``` 248 | format: 249 | - [name](link) [other links] 250 | - author1, author2, and author3... 251 | - description 252 | ``` 253 | 254 | - [Emei](https://github.com/FrankTianTT/emei) 255 | - Description: Emei is an open source Python library for developing of causal model-based reinforcement learning algorithms by providing a standard API to communicate between learning algorithms and environments, as well as a standard set of environments compliant with that API. Emei is a re-encapsulation of Openai Gym(will be replaced by Gymnasium soon). 256 | - [CausalMBRL](https://github.com/dido1998/CausalMBRL#chemistry-environment) 257 | - Nan Rosemary Ke, Aniket Didolkar, Sarthak Mittal, Anirudh Goyal, Guillaume Lajoie, Stefan Bauer, Danilo Rezende, Yoshua Bengio, Michael Mozer, Christopher Pal 258 | - Description: The CausalMBRL dataset is created to test the causal learning abilities of model-based reinforcement learning agents. It contains 2 environments: The Physics Environment and The Chemistry Environment. Both the environments consist of blocks of various colors, shapes, and weights placed in a grid. For both the environments,there exists a ground-truth causal graph which dictates how the blocks interact. This graph is unknown to the model and should be discovered by it through interactions with the environment. 259 | - [CausalWorld](https://github.com/rr-learning/CausalWorld) [[Website](https://sites.google.com/view/causal-world/home)] 260 | - CausalWorld is an open-source simulation framework and benchmark for causal structure and transfer learning in a robotic manipulation environment (powered by bullet) where tasks range from rather simple to extremely hard. Tasks consist of constructing 3D shapes from a given set of blocks - inspired by how children learn to build complex structures. 261 | - [Contextual Grid-world](https://github.com/eghbalz/contextual-gridworld) 262 | - Hamid Eghbal-zadeh\*, Florian Henkel\* and Gerhard Widmer 263 | - Description: Agents are trained on a set of training contexts, and are evaluated on two different sets of testing contexts. The aim is to evaluate how well agents captured the causal variables from the training, and can reason to correctly infer and generalise to new (test) contexts. 264 | 265 | 266 | ## Others 267 | 268 | - [Blog] [因果科学 x Agents | TMLR (2023) 因果强化学习最新综述](https://zhuanlan.zhihu.com/p/668830312): A Chinese blog post about our survey on causal reinforcement learning, and its English version is HERE: [Causality x Agents: TMLR (2023) The Latest Survey on Causal Reinforcement Learning](https://2wildkids.com/posts/2023/12/CausalRL/). Eager to explore the field quickly? This blog is for you! 269 | - [Project] [Causal-MBRL](https://github.com/polixir/causal-mbrl): a toolbox for facilitating the development of Causal Model-based Reinforcement learning algorithms. 270 | - [Blog] [Introduction to Causal RL by Chaochao Lu](https://causallu.com/2018/12/31/introduction-to-causalrl/): a blog post about how causal reinforcement learning can improve healthcare and medicine by using causal reinforcement learning to learn from fewer data, adapt to changing environments, and handle confounding factors. 271 | - [Blog] [Causal Reinforcement Learning: A Primer](https://stjohngrimbly.com/causal-reinforcement-learning/): A blog series that introduces and explains Elias Bareinboim’s tutorial on Causal RL at ICML 2020. 272 | 273 | 274 | ## Contributing 275 | 276 | If you are interested in contributing, please refer to [HERE](CONTRIBUTING.md) for instructions in contribution. 277 | 278 | 279 | ## License 280 | 281 | This project is released under the Apache 2.0 license. 282 | 283 | 284 | 285 | --------------------------------------------------------------------------------