Closed WangJuan6 closed 2 months ago
You can custom your own networks, and pass it into the input argument of DI-engine's policy. Here is the concrete implementation of this argument.
Hi, @PaParaZz1 Thank you for your reply. Is there a plan to set encoder parameters in MAVAC that are similar to how it’s done in VAC? https://github.com/opendilab/DI-engine/blob/7f951592a3d7b39c8fda44081fc40002f0ee27fc/ding/model/template/vac.py#L43 I think this would be convenient for network customization. Thanks, Juan
We will add this argument like that in VAC in a week.
Thanks, that’s good news! I’m looking forward to the update.
We have added this feature in the above commit.
Dear Author,
I want to use the mappo algorithm in the custom multi-agent environment. My observation consists of two parts: agent_state and global_state. Specifically: The dimensions of agent_state are given by H1 × W1 × C1. The dimensions of global_state are given by H2 × W2 × C2.
I noticed that the parameters of agent_obs_shape and global_obs_shape in MAVAC can be either integers or sequences:
So, I set the observation shape in the config file:
However, the error:
occurred in:
when I use the observation shape mentioned above.
How can I utilize custom networks, or is there an alternative method for handling sequence-type inputs other than flattening the array to 1D?
Thank you for your assistance!
Best regards, Juan