higgsfield/RL-Adventure-2

Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

238 best points · 14 comments · 4 Hacker News posts · 6,294 GitHub stars · View on GitHub

Hacker News discussions

• Reinforcement Learning: From Zero to State of the Art with Pytorch 4 (238 points, 14 comments, by codentropy, 2018-06-07)
• RL-Adventure-2: PyTorch tutorial of a2c/ppo/acer/ddpg/td3/soft a2c/gail/her (3 points, 0 comments, by higgsfield, 2018-05-27)
• Reinforcement Learning Tutorial: From Zero to State of the Art (2 points, 0 comments, by codentropy, 2018-06-04)
• Higgsfield/RL-Adventure-2: PyTorch4 tutorial of: actor critic etc. (1 points, 0 comments, by axiomdata316, 2018-05-29)