Closed GoingMyWay closed 2 years ago
Hi, we didn’t conduct ablation without the transformer as it is a vital part of the architecture, but it would be interesting to check the performance in this setup. I hypothesize that the performance would drop significantly as the original dreamer algorithm performs poorly in marl environments
@vladimirrim, Hi Thanks for the clarification. I am also curious that during the trajectory generation procedure, is the transformer also used in "imagination"?
Yes, It is important both for training and execution phases.
Yes, It is important both for training and execution phases.
Dear @vladimirrim, I see. Did some reviewers raise concerns about using the transformer in "imagination"? In MARL, it is challenging to train a world model without using global information since agents have partial observations.
Dear @vladimirrim, I am curious whether you tried another model-based modelling method for MARL. I found without exploiting the global information, the most useful method is to mix all local information to adjust the training of each agent's local world model, like CTDE or the mixing network of QMIX and other Dec-POMDP-based MARL methods. Incorporating the world model into MARL is non-trivial.
Hi, the transformer is used in your code. Without the transformer, can your method also gain good performance?