Emergent-Multiagent-Strategies
IC3Net
Emergent-Multiagent-Strategies | IC3Net | |
---|---|---|
1 | 2 | |
38 | 202 | |
- | 0.0% | |
0.0 | 0.0 | |
over 1 year ago | 7 months ago | |
Python | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Emergent-Multiagent-Strategies
-
PPO with Transformer or Attention Mechanism
Not stable_baselines but I have an implementation of Attention + PPO in a multi-agent setting: https://github.com/Ankur-Deka/Emergent-Multiagent-Strategies
IC3Net
What are some alternatives?
Competitive-Programming
smac - SMAC: The StarCraft Multi-Agent Challenge
DI-engine - OpenDILab Decision AI Engine
Mava - 🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX
pumpkin - The MAS Demonic Surveillance Platform. 🎃 [Moved to: https://github.com/scandale-project/pumpkin]
malib - A parallel framework for population-based multi-agent reinforcement learning.
pymarl2 - Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)
Ray - Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
wandb - 🔥 A tool for visualizing and tracking your machine learning experiments. This repo contains the CLI and Python API.