maddpg

We have hosted the application maddpg in order to run this application in our online workstations with Wine or directly.

Quick description about maddpg:

MADDPG (Multi-Agent Deep Deterministic Policy Gradient) is the official code release from OpenAI�s paper Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. The repository implements a multi-agent reinforcement learning algorithm that extends DDPG to scenarios where multiple agents interact in shared environments. Each agent has its own policy, but training uses centralized critics conditioned on the observations and actions of all agents, enabling learning in cooperative, competitive, and mixed settings. The code is built on top of TensorFlow and integrates with the Multiagent Particle Environments (MPE) for benchmarking. Researchers can use it to reproduce the experiments presented in the paper, which demonstrate how agents learn behaviors such as coordination, competition, and communication. Although archived, MADDPG remains a widely cited baseline in multi-agent reinforcement learning research and has inspired further algorithmic developments.

Features:

• Implementation of Multi-Agent DDPG with centralized critics
• Supports cooperative, competitive, and mixed-agent settings
• TensorFlow-based training pipeline for multi-agent RL
• Compatible with Multiagent Particle Environments (MPE)
• Scripts for reproducing results from the original paper
• Reference implementation for research in multi-agent RL

Programming Language: Python.
Categories: