Mava icon indicating copy to clipboard operation
Mava copied to clipboard

🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX

Results 160 Mava issues
Sort by recently updated
recently updated
newest added

### 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...

bug

### 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...

bug

### Feature Add support to run Mava systems as a single process program rather than a distributed program using Launchpad. It is very hard to debug Mava systems because of...

enhancement

### Describe the bug https://github.com/instadeepai/Mava/blob/develop/mava/specs.py#L68 assumes that agents from all environments are named with the convention `type_identifier` and hence using `split` to extract type. This is in some environments such...

bug

### 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...

enhancement

### Describe the bug We need to standardize how we handle observation networks. We have the following options: 1. Have both critic and policy networks update the obs network vars....

bug

**Describe the bug** Nested `tf.function` decorators are causes TF to constantly retrace which is could cause significant performance and memory issues. **Additional context** I think this bug creeped in when...

bug

**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...

bug

### Please describe the purpose of the feature. Is it related to a problem? Currently docker images are pushed when you tag PR with the `benchmark` tag. If you push...

enhancement

### Please describe what needs to be maintained? Rename train_loop_fn to exec_loop_fn since this is line line with its purpose ### Describe the outcome you'd like Variable name reflects purpose...