Distributed Deep Reinforcement Learning by Ray and TensorFlow.
This framework inspired by general-purpose RL training system Rapid from OpenAI.
Rapid framework:
This framework:
Tutorial (Chinese version)
In short. This framework divides the reinforcement learning process into five parts:
简单实验对比:
实验:LunarLanderContinuous-v2
算法:SAC
未调参,sac和dsac参数相同,dsac的worker数量:1。GPU:GTX1060
(dsac: distributed sac)