mfrl
mfrl copied to clipboard
mlii
Mean Field Multi-Agent Reinforcement Learning
Your code seems to be written based on TensorFlow 1.X. Have you considered using TensorFlow 2.X or PyTorch?
If there is no global state，Can agents use MF-Q when they only have local observations？
Do you have an implementation of Gaussian Squeeze (GS)？ Do you have the pytorch version of the average field multi-agent reinforcement learning code？
Recently, I have run the train_battle.py and battle.py. However, I found the performance of one algorithms may vary quite obviously in the battle game. I consider this is quite normal....
hi,i am trying to reproduce the battle game (red army use MFQ and blue army use DQN.) i trained the model and find both algorithums has a negative reward.and the...
 问题的初衷： 我想要把用MFAC训练好的模型和用AC训练好的模型进行对比，让这两个算法进行交叉战斗实验。在终端运行如下：python battle.py --algo mfac --oppo ac --idx 10 10 仍然抛出异常： ValueError: The passed save_path is not a valid checkpoint: /home/lzh/postgraduate project/mfrl-master/data/models/mfac-0/mfac_1 疑惑的点： 1）如何运行battle.py 2) 参数--idx 如何设置parser.add_argument('--idx', nargs='*', required=True)...
I use Ubuntu System, and when I try run "python3 train_battle.py --algo mfac", I got an Error "ModuleNotFoundError: No module named 'magent", and "AttributeError: 'GridWorld' object has no attribute 'game'"....
Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning 您好，这篇论文的代码，方便发我一份吗？ [email protected] Hello, can you send me a copy of the code for this paper?
Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning 您好，这篇论文的代码，方便发我一份吗？ [email protected] Hello, can you send me a copy of the code for this paper?
code
Hello, I'm watching your paper "Efficient Ride Sharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning", and I'm very interested. Can you mention relevant codes and data sets? I promise...
