THE FUTURE IS HERE

20240219 Reinforcement Learning, PPO, OpenAI Gym's Atari "Pong" pixel game

๐Ÿ‘‰ Reinforcement Learning, PPO, OpenAI Gym’s ๐€๐ญ๐š๐ซ๐ข “๐๐จ๐ง๐ ” pixel game

โ–ช๏ธ ๐Ÿ๐ฎ๐ฅ๐ฅ ๐œ๐ฎ๐ซ๐ซ๐ข๐œ๐ฎ๐ฅ๐ฎ๐ฆ – https://www.evernote.com/shard/s139/sh/49b549b3-040e-6829-3800-85e830516134/sdITMf7KBEt6jP_X-hSjU2INJdgfpL8VBCtAS7DHs0C61DeCnJJRR_Yn2Q

โ–ช๏ธ ๐ง๐จ๐ญ๐ž๐›๐จ๐จ๐ค๐ฌ
– PPO without clipping
https://drive.google.com/file/d/17-HyqTB121RjHvJ03GzY81eGxmmpjY3t
https://github.com/Nov05/Google-Colaboratory/blob/master/20240217_pong_REINFORCE.ipynb
– PPO with clipping
https://drive.google.com/file/d/1lAvn0_pPyFBnWJ4HPyXfVBhh7qjPo2gP
https://github.com/Nov05/Google-Colaboratory/blob/master/20240218_pong_PPO.ipynb

#reinforcementlearning #machinelearning