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.
The next generation deep reinforcement learning tookit
| Date | Stars |
|---|---|
| 2026-07-24 | 3465 |
| 2026-07-25 | 3465 |
| 2026-07-28 | 3465 |
| 2026-07-30 | 3465 |
| 2026-07-31 | 3466 |
| 2026-08-06 | 3466 |
Today
— stars today
This week
+1 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.03%/day
# AI-Optimizer AI-Optimizer is a next-generation deep reinforcement learning suit, providing rich algorithm libraries ranging from model-free to model-based RL algorithms, from single-agent to multi-agent algorithms. Moreover, AI-Optimizer contains a flexible and easy-to-use distributed training framework for efficient policy training.  AI-Optimizer now provides the following built-in libraries, and more libraries and implementations are coming soon. - [Multiagent Reinforcement learning](multiagent-rl) - [Self-supervised Representation Reinforcement Learning](https://github.com/TJU-DRL-LAB/self-supervised-rl) - [Offline Reinforcement Learning](offline-rl-algorithms) - [Transfer and Multi-task Reinforcement Learning](https://github.com/TJU-DRL-LAB/transfer-and-multi-task-reinforcement-learning) - [Model-based Reinforcement Learning](modelbased-rl) ## Multiagent Reinforcement Learning (MARL) The Multiagent RL repo contains the released codes of representative research works of TJU-RL-Lab on Multiagent Reinforcement Learning (MARL). ### ❓ Problem to Solve <p align="center"><img align="center" src="./multiagent-rl/assets/representative_applications.png" alt="Four representative applications of recent successes of MARL: unmanned aerial vehicles, game of Go, Poker games, and team-battle video games."/></p> Multi-agent reinforcement learning (MARL) has successfully addressed many complex real-world problems, such as playing the game of Go ([AlphaGo](https://idp.nature.com/authorize/casa?redirect_uri=https://www.nature.com/articles/nature16961%257D&casa_token=JKjRDdaog1cAAAAA:cwpvaRtkWOQi-K-NGT2AT9bNM1kcA5NgXWU7MVIdrI6poJ8FwDxyunnDEpGaOuoUxfA4RzOumao3MqS-8mU), [AlphaGo Zero](https://www.nature.com/articles/nature24270?sf123103138=1)), playing real-time multi-player strategy games ([StarCraft II](https://www.nature.com/articles/s41586-019-1724-z?), [Dota 2](https://arxiv.org/abs/1912.06680), [Honor of Kings](https://arxiv.org/abs/2011.12895))，playing card games ([Poker](https://www.science.org/doi/abs/10.1126/science.aay2400?casa_token=YpsKCNt7LNwAAAAA:POhK0ufRyfzaHXWiywSHPk6nvzugQVsTNYdSZyteYTkRRPA4zccUvmnOBYC2DBFcIytHN9FPqZ-s6SUY), [no-limit Poker](https://www.onlinecasinoground.nl/wp-content/uploads/2018/10/Libratus-super-human-no-limit-poker-Sandholm-Brown.pdf)), [robotic control](https://arxiv.org/abs/1709.06011) and autonomous driving ([Smarts](https://arxiv.org/abs/2010.09776)). However, MARL suffers from several challenges in theoretical analysis, in addition to those that arise in single-agent RL. We summarize below the challenges that we regard as fundamental in developing theories for MARL. - **The curse of dimensionality (scalability) issue** - **Non-stationarity** - **Non-Unique Learning Goals** - **Exploration–exploitation tradeoff** - **Multiagent credit assignment problem** - **Partial observability** - **Hybrid action** Our target is to design MARL algorithms which could solve or alleviate the problems mentioned above and promote the deployment and landing of MARL in more real-world applications. ### ⭐️ Core Directions We carry out our studies according to the challenges mentioned above. To solve the the curse of dimensionality issue, we design a series of scalable multiagent neural networks which could efficiently reduce the size of the search space by leveraging the [permutation invariance and permutation equivariance properties](https://arxiv.org/abs/2203.05285), explicitly taking the [action semantics](https://arxiv.org/abs/1907.11461) into consideration, etc. To better make a balance of the exploration–exploitation tradeoff, we propose Progressive Mutual Information Collaboration to achieve more efficient cooperative exploration... An overall picture of the proposed methods is shown below. <p align="center"><img align="center" src="./multiagent-rl/assets/our-work.png" alt="our solutions" /></p>
Excerpt of 20,643 characters
Read on GitHub
139
79
Fei_Ni
57
34
29
17
11
mangoz
2
Weixun Wang · DRL/MAS
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:f80b28e5740ae04e, topic:reinforcement-learning, desc:reinforcement learning, readme:reinforcement learning
matched fp:f80b28e5740ae04e, topic:deep-learning, readme:training framework, readme:distributed training