Best Alternatives to on-policy
LLM InfraΒ·β
2.0kΒ·MIT
This is the official implementation of Multi-Agent PPO (MAPPO).
#Multi-Agent Reinforcement Learning#PPO#MAPPO#Reinforcement Learning#PyTorch
01
Best Alternatives to on-policy
ToolDescriptionStarsLicenseUpdated
01
MetaGPT
MetaGPTπ The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
β
68.4k
MIT
4mo ago
Details β02
cua
cuaOpen-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
β
17.3k
MIT
1d ago
Details β03
xLAM
xLAMxLAM: A Family of Large Action Models to Empower AI Agent Systems
β
621
APACHE
9mo ago
Details β04
mini-swe-agent
mini-swe-agentThe 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepoβbut scores >74% on SWE-bench verified!
β
4.7k
β
5d ago
Details β05
youtu-agent
youtu-agentA simple yet powerful agent framework that delivers with open-source models
β
4.6k
NOASSERTION
2mo ago
Details β06
FedML
FedMLFEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs on any GPU cloud or on-premise cluster. Built on this library, TensorOpera AI (https://TensorOpera.ai) is your generative AI platform at scale.
β
4.0k
Apache-2.0
7mo ago
Details β07
chatarena
chatarenaChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
β
1.5k
APACHE
9mo ago
Details β08
AgileRL
AgileRLStreamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary hyperparameter optimization.
β
921
β
1d ago
Details β02
Side-by-Side Comparison
| Field | on-policy | MetaGPT | cua | xLAM |
|---|---|---|---|---|
| Category | LLM Infra | LLM Infra | LLM Infra | LLM Infra |
| Stars | β 2.0k | β 68.4k | β 17.3k | β 621 |
| License | MIT | MIT | MIT | APACHE |
| Updated | 1y ago | 4mo ago | 1d ago | 9mo ago |
| Open Source | Yes | Yes | Yes | Yes |
03
Compare on-policy With Others
04
FAQ
What is on-policy?
This repository implements MAPPO, a multi-agent variant of PPO, widely used in cooperative multi-agent games and research. It provides robust implementations for various multi-agent environments like StarCraft II, Hanabi, and Google Research Football, along with detailed training scripts and hyperparameter guidance.
What is the best alternative to on-policy?
MetaGPT is the top-rated alternative to on-policy in the LLM Infra category.
Is there a free alternative to on-policy?
MetaGPT is a free, open-source alternative.
Is on-policy open source?
Yes, on-policy is open source on GitHub, licensed under MIT.