Closed rsanchezmo closed 7 months ago
hiya, thanks for your attention! yep, we used to considered adding an extra attention block at the beginning of encoder for modeling history information, and we believe it is very likely to improve performance further especially in partially observable scenarios.
actually, I've been meaning to implement this feature to this repo, but haven't done it yet due to procrastinations. (struggling for this.....)
Hi!
Do you plan to keep the same input [joint observations history]? Do you think now passing previous actions as a new input would improve the model, as well as previous rewards, etc [based on Decision Transformer or ODT]?
Thanks in advance!
Hi!
Do you plan to keep the same input [joint observations history]? Do you think now passing previous actions as a new input would improve the model, as well as previous rewards, etc [based on Decision Transformer or ODT]?
Thanks in advance!
Hello, I also found this problem in the research, and I am trying it recently. Could I discuss this problem with you?
@MPHarryZhang reach me by email!
Hi! Have you considered to add previous observations from the agents to the feed the transformer? The encoder should pay attention to relations between agents by also considering the temporal dimension, which may lead to a better action planning.
As far as I know, the current implementation of MAT does not support previous observations and because of that, it has no memory.