Source code for paper: An Efficient Transfer Learning Framework for Multiagent Reinforcement Learning

A PyTorch implementation of SEED, originally created by Google Research for TensorFlow 2.

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Modularized Implementation of Deep RL Algorithms in PyTorch

Distributed Multi-Agent Cooperation Algorithm based on MADDPG with prioritized batch data.

Never use print for debugging again

中文古诗自动作诗机器人，x炸天，基于tensorflow1.10 api，正在积极维护升级中，快star，保持更新！