peterwangx

ddzAI

斗地主服务器AI 采用c++封装成动态库 lua直接调用.so库 模拟真人，采用权值加决策，用到少量的人工智能

distributed-ppo

This is an pytorch implementation of Distributed Proximal Policy Optimization(DPPO).

drl

DQN-based-UAV-3D_path_planer

RLGF is a general training framework suitable for UAV deep reinforcement learning tasks. And integrates multiple mainstream deep reinforcement learning algorithms(SAC, DQN, DDQN, PPO, Dueling DQN, DDPG).

peterwangx/ddzAI

斗地主服务器AI 采用c++封装成动态库 lua直接调用.so库 模拟真人，采用权值加决策，用到少量的人工智能

peterwangx/distributed-ppo

This is an pytorch implementation of Distributed Proximal Policy Optimization(DPPO).

peterwangx/drl