Тёмный
Max Lapan
Max Lapan
Max Lapan
Подписаться
3rd edition, ch16: TRPO Ant on PyBullet
0:34
4 месяца назад
Minute engine - 3D printed
0:36
3 года назад
Wrong moving objective
0:31
5 лет назад
Ch06: Pong with score -3
1:17
5 лет назад
Ch06: Pong with score -12
1:28
5 лет назад
Ch06: Pong with score -18
1:53
5 лет назад
Ch06: Pong with score -15
1:12
5 лет назад
Ch06: Pong with score -9
2:07
5 лет назад
Ch06: Pong with score -6
1:33
5 лет назад
Ch06: Pong with score 0
1:32
5 лет назад
Ch06: Pong with score 12
1:07
5 лет назад
Ch06: Pong with score 15
1:13
5 лет назад
Ch06: Pong with score 3
1:09
5 лет назад
Ch06: Pong with score 6
1:47
5 лет назад
Ch06: Pong with score 9
1:09
5 лет назад
Комментарии
@inserthere6387
@inserthere6387 Год назад
awesome stuff Max will be trying this, seems very promising in a short training time span; will be using a prioritized replay buffer to see if it makes a difference! thanks again Max for one of the best rl books on the market; can't wait for your next book!!!!
@smithralph1120
@smithralph1120 2 года назад
Thankyou
@smithralph1120
@smithralph1120 2 года назад
Reading your book right now, from China Jiangsu.
@spinity8468
@spinity8468 4 года назад
Your book is awesome Max! :D I am studying "Deep Reinforcement Learning Hands-on". Can you tell me what are the major different between that book and your second edition of this book?
@MaxLapan
@MaxLapan 4 года назад
Hi! Thanks! Differences were covered in my blog post on medium: link.medium.com/PPJmqLm2J6
@billykotsos4642
@billykotsos4642 4 года назад
Nice!