feat: readme revamp

docs/CONTRIBUTING.md

@@ -39,7 +39,7 @@ pre-commit run --all-files
 
 ## Naming Conventions
 ### Branch Names
-We name our feature and bugfix branches as follows - `feature/[BRANCH-NAME]`, `bugfix/[BRANCH-NAME]` or `maintenance/[BRANCH-NAME]`. Please ensure `[BRANCH-NAME]` is hyphen delimited.
+We name our feature and bugfix branches as follows - `feat/[BRANCH-NAME]`, `fix/[BRANCH-NAME]`. Please ensure `[BRANCH-NAME]` is hyphen delimited.
 ### Commit Messages
 We follow the conventional commits [standard](https://www.conventionalcommits.org/en/v1.0.0/).
 

docs/DETAILED_INSTALL.md

@@ -1,12 +1,11 @@
 # Detailed installation guide
 
 ### Conda virtual environment
-We recommend using `conda` for package management. These instructions should allow you to install and run mava.
+We recommend using [uv](https://docs.astral.sh/uv/) for package management. These instructions should allow you to install and run mava.
 
-1. Create and activate a virtual environment
+1. Install `uv`
 ```bash
-conda create -n mava python=3.12
-conda activate mava
+curl -LsSf https://astral.sh/uv/install.sh | sh
 ```
 
 2. Clone mava
@@ -15,19 +14,22 @@ git clone https://github.com/instadeepai/Mava.git
 cd mava
 ```
 
-3. Install the dependencies
+3. Create and activate a virtual environment and install requirements
 ```bash
-pip install -e .
+uv venv -p=3.12
+source .venv/bin/activate
+uv pip install -e .
 ```
 
-4. Install jax on your accelerator. The example below is for an NVIDIA GPU, please the [official install guide](https://github.com/google/jax#installation) for other accelerators
+4. Install jax on your accelerator. The example below is for an NVIDIA GPU, please the [official install guide](https://github.com/google/jax#installation) for other accelerators.
+Note that the Jax version we use will change over time, please check the [requirements.txt](https://github.com/instadeepai/Mava/blob/develop/requirements/requirements.txt) for our latest tested Jax verion.
 ```bash
-pip install "jax[cuda12]==0.4.30"
+uv pip install "jax[cuda12]==0.4.30"
 ```
 
 5. Run a system!
 ```bash
-python mava/systems/ppo/ff_ippo.py env=rware
+python mava/systems/ppo/anakin/ff_ippo.py env=rware
 ```
 
 ### Docker

mava/systems/mat/README.md

@@ -0,0 +1,6 @@
+# Multi-agent Transformer
+
+We provide an implementation of the Multi-agent Transformer algorithm in JAX. MAT casts cooperative multi-agent reinforcement learning as a sequence modeling problem where agent observations and actions are treated as a sequence. At each timestep the observations of all agents are encoded and then these encoded observations are used for auto-regressive action selection.
+
+## Relevant paper:
+* [Multi-Agent Reinforcement Learning is a Sequence Modeling Problem](https://arxiv.org/pdf/2205.14953)

mava/systems/ppo/README.md

@@ -0,0 +1,17 @@
+# Proximal Policy Optimization
+
+We provide the following four multi-agent extensions to [PPO](https://arxiv.org/pdf/1707.06347) following the Anakin arhitecture.
+
+* [ff-IPPO](https://github.com/instadeepai/Mava/blob/develop/mava/systems/ppo/anakin/ff_ippo.py)
+* [ff-MAPPO](https://github.com/instadeepai/Mava/blob/develop/mava/systems/ppo/anakin/ff_mappo.py)
+* [rec-IPPO](https://github.com/instadeepai/Mava/blob/develop/mava/systems/ppo/anakin/rec_ippo.py)
+* [rec-MAPPO](https://github.com/instadeepai/Mava/blob/develop/mava/systems/ppo/anakin/rec_mappo.py)
+
+In all cases IPPO implies that it is an implementation following the independent learners MARL paradigm while MAPPO implies that the implementation follows the centralised training with decentralised execution paradigm by having a centralised critic during training. The `ff` or `rec` in the system names implies that the policies are MLPs or have a [GRU](https://arxiv.org/pdf/1406.1078) memory module to help learning despite partial observability in the environment.
+
+In addition to the Anakin-based implementations, we also include a Sebulba-based implementation of [ff-IPPO](https://github.com/instadeepai/Mava/blob/develop/mava/systems/ppo/sebulba/ff_ippo.py) which can be used on environments that are not written in JAX and adhere to the Gymnasium API.
+
+## Relevant papers:
+* [Proximal Policy Optimization Algorithms](https://arxiv.org/pdf/1707.06347)
+* [The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games](https://arxiv.org/pdf/2103.01955)
+* [Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?](https://arxiv.org/pdf/2011.09533)

mava/systems/q_learning/README.md

@@ -0,0 +1,14 @@
+# Q Learning
+
+We provide two Q-Learning based systems that follow the independent learners and centralised training with decentralised execution paradigms:
+
+* [rec-IQL](https://github.com/instadeepai/Mava/tree/feat/develop/mava/systems/q_learning/anakin/rec_iql.py)
+* [rec-QMIX](https://github.com/instadeepai/Mava/tree/feat/develop/mava/systems/q_learning/anakin/rec_qmix.py)
+
+`rec-IQL` is a multi-agent version of DQN that uses double DQN and has a GRU memory module and `rec-QMIX` is an implementation of QMIX in JAX that uses monontic value function decomposition.
+
+## Relevant papers:
+* [Playing Atari with Deep Reinforcement Learning](https://arxiv.org/pdf/1312.5602)
+* [Multiagent Cooperation and Competition with Deep Reinforcement Learning](https://arxiv.org/pdf/1511.08779)
+* [QMIX: Monotonic Value Function Factorisation for
+Deep Multi-Agent Reinforcement Learning](https://arxiv.org/pdf/1803.11485)

mava/systems/sable/README.md

@@ -0,0 +1,31 @@
+# Sable
+
+Sable is an algorithm that was developed by the research team at InstaDeep. It also casts MARL as a sequence modelling problem and leverages the [advantage decompostion theorem](https://arxiv.org/pdf/2108.08612) through auto-regressive action selection for convergence guarantees and can scale to thousands of agents by leveraging the memory efficiency of Retentive Networks.
+
+We provide two Anakin based implementations of Sable:
+* [ff-sable](https://github.com/instadeepai/Mava/blob/develop/mava/systems/sable/anakin/ff_sable.py)
+* [rec-sable](https://github.com/instadeepai/Mava/blob/develop/mava/systems/sable/anakin/rec_sable.py)
+
+Here `ff` implies that the algorithm retains no memory over time but treats only the agents as the sequence dimension while `rec` implies that the algorithms maintains a memory over both agents and time for long context memory in partially observable environments.
+
+For an overview of how the algorithm works, please see the diagram below. For a more detailed overview please see the associated [paper](https://arxiv.org/pdf/2410.01706).
+
+<p align="center">
+    <a href="../../../docs/images/algo_images/sable-arch.png">
+        <img src="../../../docs/images/algo_images/sable-arch.png" alt="Sable Arch" width="80%"/>
+    </a>
+</p>
+
+<p style="text-align:left; margin-top: 10px;">
+<em>Sable architecture and execution.</em> The encoder receives all agent observations
+\( o_t^1, \dots, o_t^N \) from the current timestep \( t \) along with a hidden state
+\( h_{t-1}^{\text{enc}} \) representing past timesteps and produces encoded observations
+\( \hat{o}_t^1, \dots, \hat{o}_t^N \), observation-values \( v(\hat{o}_t^1), \dots, v(\hat{o}_t^N) \),
+and a new hidden state \( h_t^{\text{enc}} \).
+The decoder performs recurrent retention over the current action \( a_t^{m-1} \), followed by cross attention with the encoded observations, producing the next action \( a_t^m \). The initial hidden states for recurrence over agents in the decoder at the current timestep are
+\( (h_{t-1}^{\text{dec}_1}, h_{t-1}^{\text{dec}_2}) \), and by the end of the decoding process, it generates the updated hidden states \( (h_t^{\text{dec}_1}, h_t^{\text{dec}_2}) \).
+</p>
+
+## Relevant paper:
+* [Performant, Memory Efficient and Scalable Multi-Agent Reinforcement Learning](https://arxiv.org/pdf/2410.01706)
+* [Retentive Network: A Successor to Transformer for Large Language Models](https://arxiv.org/pdf/2307.08621)

mava/systems/sac/README.md

@@ -0,0 +1,16 @@
+# Soft Actor-Critic
+
+We provide the following three multi-agent extensions to the Soft Actor-Critic (SAC) algorithm.
+
+* [ff-ISAC](https://github.com/instadeepai/Mava/blob/feat/develop/mava/systems/sac/anakin/ff_isac.py)
+* [ff-MASAC](https://github.com/instadeepai/Mava/blob/feat/develop/mava/systems/sac/anakin/ff_masac.py)
+* [ff-HASAC](https://github.com/instadeepai/Mava/blob/feat/develop/mava/systems/sac/anakin/ff_hasac.py)
+
+`ISAC` is an implementation following the independent learners MARL paradigm while `MASAC` is an implementation that follows the centralised training with decentralised execution paradigm by having a centralised critic during training. `HASAC` follows the henterogeneous agent learning paradigm through sequential policy updates. The `ff` prefix to the algorithm names indicate that the algorithms using MLP-based policy networks.
+
+## Relevant papers
+* [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://arxiv.org/pdf/1801.01290)
+* [Multi-Agent Actor-Critic for Mixed
+Cooperative-Competitive Environments](https://arxiv.org/pdf/1706.02275)
+* [Robust Multi-Agent Control via Maximum Entropy
+Heterogeneous-Agent Reinforcement Learning](https://arxiv.org/pdf/2306.10715)