Mava

Mava copied to clipboard

### Please describe the purpose of the feature. Is it related to a problem? A tutorial notebook for creating an IPPO system to accompany Mava Jax release. ### Describe the...

RuanJohn

### Describe the benchmarking experiment/task Benchmark the Mava Jax IPPO system on the same MPE and SMAC tasks as in [this PPO paper](https://arxiv.org/abs/2103.01955). ### Hypothesis/expected behavior or outcome Match the...

RuanJohn

### Please describe what needs to be maintained? Update the Jax IPPO readme before Jax release. ### Describe the outcome you'd like Jax IPPO readme has an outline of the...

RuanJohn

### Please describe what needs to be maintained? Ensure that all jax ippo functions have detailed and descriptive docstrings and that the code is well commented before the Jax release.

RuanJohn

### Please describe the purpose of the feature. Is it related to a problem? Create an automated pipeline to easily run experiments on the SMAC environments as used in this...

DriesSmit

### Describe the benchmarking experiment/task The main goal of the Mava JAX release is to match the performance of [this](https://arxiv.org/abs/2103.01955) paper. Our notion page, documenting our progress, can be found...

DriesSmit

### Please describe the purpose of the feature. Is it related to a problem? This feature would allow the critic network to utilise recurrent neural networks. Recurrent networks should improve...

DriesSmit

### Feature Make the executor have an environment loop instead of the other way around. It makes more intuitive sense to run the executor instead of the environment loop (which...

DriesSmit

### What do you want to investigate? Determine a better Mava standard that would make the executors and trainers more composable. We want to make it easy to add new...

DriesSmit

[INVESTIGATION] PettingZoo Environments Wrappers

1

Are there any examples of how to wrap and use a pettingzoo environment in MAVA?

davidedomini