opendilab/ACE
[AAAI 2023] Official PyTorch implementation of paper "ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency".
Introduces bidirectional action-dependency modeling to capture inter-agent coordination patterns, enabling agents to reason about both how their actions affect teammates and how teammate actions constrain their own decisions. Integrates with SMAC (StarCraft Multi-Agent Challenge) and Google Research Football environments, providing end-to-end training pipelines with PyTorch-based Q-learning optimized for cooperative scenarios with explicit action dependency graphs.
238 stars. No commits in the last 6 months.
Stars
238
Forks
12
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 07, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/opendilab/ACE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
facebookresearch/BenchMARL
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL...
Toni-SM/skrl
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with...
datamllab/rlcard
Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
utiasDSL/gym-pybullet-drones
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
koulanurag/ma-gym
A collection of multi agent environments based on OpenAI gym.