Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges
| Date | Stars |
|---|---|
| 2026-07-31 | 281 |
| 2026-08-01 | 281 |
| 2026-08-02 | 281 |
| 2026-08-06 | 281 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Awesome Explainable Reinforcement Learning [](https://arxiv.org/abs/2211.06665) [](https://github.com/sindresorhus/awesome) [](https://github.com/topics/awesome) [](https://github.com/topics/document) A list of selected paper and possible corresponding codes in our review paper [A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges](https://arxiv.org/abs/2211.06665). *If you find there is a missed paper or a possible mistake in our survey, please feel free to email me (<[email protected]>) or pull a request here. I am more than glad to receive your advice. Thanks!* ## Citation If you find this survey useful for your research, please consider citing ``` @article{qing2022XRLsurvey, title={A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges}, author={Qing, Yunpeng and Liu, Shunyu and Song, Jie and Wang, Huiqiong and Song, Mingli}, journal={arXiv preprint arXiv:2211.06665}, year={2022} } ``` ## 🔥 News - [x] *2025.2.10:* We have updated our review paper with the latest revisions and incorporated newly published research from 2023 to 2024. - [x] *2023.11.01:* We have updated our review paper with the latest revisions and incorporated newly published research from 2022 to 2023. ## Table of Contents - [Overview](#Overview) - [Surveys](#Surveys) - [Explainability in RL](#Explainability-in-RL) - [Agent Model Explaining](#Agent-Model-Explaining) - [Reward Explaining](#Reward-Explaining) - [State Explaining](#State-Explaining) - [Task Explaining](#Task-Explaining) - [Human knowledge for RL paradigm](#Human-knowledge-for-RL-paradigm) - [Explainable AI Library](#A-summary-of-Explainable-AI-library) ## ✨ Overview - [x] **📖 RL paradigm-based Explainable RL Taxonomy** - [x] **👓 Review of human knowledge-based RL explainability** - [x] **🚀 List of Current XRL research literatures and codes links** <!-- We review current explainable reinforcement learning framework and explainability of human knowledge-based reinforcement learning framework. We creatively propose a new taxonomy for existing explainable reinforcement learning based on reinforcement learning paradigm. Specifically, we divide existing explainable reinforcement learning methods into four categories: agent model-explaining, reward-explaining, state-explaining, task-explaining as shown below: --> In this survey, we provide a comprehensive review of existing works on eXplainable Reinforcement Learning (XRL) and introduce a new taxonomy where prior works are clearly categorized into agent model-explaining, reward-explaining, state-explaining, and task-explaining methods. We also review and highlight RL methods that conversely leverage human knowledge to promote learning efficiency and performance of agents while this kind of method is often ignored in XRL field. <div align="center"> <img src="https://github.com/plankson/awesome-explainable-reinforcement-learning/blob/main/Fig/categorize.png" width="100%"> </div> <!-- The Figure above illustrate how to enhance explainability to different part of RL paradigm, which include model(agent), reward, state and the task itself. --> <!-- - Agent Model Explaining: trains the agent to be explainable by having understandable logic operation in its inner structure - Reward Explaining: reconstructs reward function towards an explainable one $r'_t$ and makes it possible to see how the goal influences the agent - State Explaining: adds a submodule for introspection to quantify the influences of different state features towards the decision-making as $w(s_{t'})$. - Task Explaining: gets an architectural level explainability in complex environments by mul
Excerpt of 36,643 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:160c21073064d7fd, topic:reinforcement-learning, name:reinforcement learning, desc:reinforcement learning
matched fp:160c21073064d7fd, name:explainable, desc:explainable