Dries
**Please describe the purpose of the feature. Is it related to a problem? ** Implement a reverb dataset component in the Mava 2.0 (redesign) codebase. Describe the solution you'd like...
### Describe the bug When running the robocup example using the image `mava:robocup-latest` I get the following error: ``` [trainer/0] File "/home/app/Mava/mava/systems/tf/maddpg/system.py", line 629, in trainer [trainer/0] _, networks =...
### Please describe the purpose of the feature. Is it related to a problem? This is a nitpick issue which might not be needed at all. But if we can...
### Feature For a small performance boost we should consider moving the tf.functions from [_minibatch_update](https://github.com/instadeepai/Mava/blob/develop/mava/systems/tf/mappo/training.py#L274) to [_step](https://github.com/instadeepai/Mava/blob/develop/mava/systems/tf/mappo/training.py#L285). ### Testing Validate that the trainer is running faster with this change. To...
### Describe the bug The executors in MADDPG pass no `set_keys` argument to the variable client. This means that the `set_keys` defaults to the `get_keys`. We don't want the executors...
### Describe the bug This makes loading from a checkpoint and resuming training problematic as new optimizers are initialised each time. ### Solution Add the optimizer states to the variable...
### Describe the bug Update the recurrent executor's [base class](https://github.com/instadeepai/Mava/blob/7e3f301eea047e4e999cd50f806f38fa0fc1ce04/mava/systems/tf/executors.py#L193) to allow for the `tf.function` the `_select_actions` function. ### Expected behavior The mypy checks should not complain when implementing a...
### Describe the bug It takes quite a long time to execute tests locally when using `make run-tests`. Alternatively, pettingzoo must first be installed when using bash to run the...
### Please describe the purpose of the feature. Is it related to a problem? To improve MAD4PG's performance while also reducing its hyperparameters which reduces possible user error. ### Describe...
**Describe the bug** The dataset sampler should still be removed from the MADDPG/MAD4PG tf.function training steps and placed outside. If the sampler is inside tf.function it can possibly sample random...