Multi-Agent-Transformer
Multi-Agent-Transformer copied to clipboard
PKU-MARL
Hi, I am very interested in this series of work and have a question about the decoder architecture. I have noticed that the decoder architecture is a little bit different...
To whom it may concern, In the paper about MAT, it is mentioned that this MARL model is processed within a central executed sequential approach, which is also complex in...
What python version are you using? pip install -r requirements.txt is not supporting below python 3.9 When I run pip install -r requirements.txt on PYTHON 3.9, I get the following...
Hello, when I tried to reproduce this work, I found that if running it multiple times at the same time (such as running six maps on the server at the...
Hi, I'm very interested in your work. And I found that there are no results of your MAT running on map "corridor" in SMAC environment showed in your paper. So...
Hello, I'm instersted in your work, and I found a question whithout explanation in paper. I noticed that the causal attention in decoder uses a different structure unlike normal transformers:...
To whom it may concern, I noticed that in forward() of ma_transformer.py, the state (cent obs) is converted into zeros. However, it seems to be an essential element for critic...
Hello, I'm a beginner with MAT. In the paper, it is mentioned that the order of agents can be permuted during the training process. Additionally, the observations are concatenated with...
**Problem**: Reproduced result is lower than the one in paper a lot **Details**: I want to reproduce the results in Bi-DexHands domain. I use the scripts which you provide directly....
Hi, Thank you again for your amazing work! i am interested in reproducing the multi map training and then few shot learning. I noticed that in the RandomStarCraft2EnvMulti code, randomizing...
