My RL agent is learning 馃 Still early in training.
Shoutout to @karpathy for his policy gradient code release. Within a couple of minutes Codex had the old dependencies updated and I was up and running!
9:32 AM 路 Jun 11, 2026 路 2K Views
Sentiment
Sentiment building, check back later.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS971BOOKMARKS6LIKES3
Kosta Derpanis (sabbatical in Zurich)@CSProfKGD
Blog: http://karpathy.github.io/2016/05/31/rl/ Code: https://github.com/karpathy/tf-agent
Kosta Derpanis (sabbatical in Zurich)@CSProfKGD
My RL agent is learning 馃 Still early in training.
Shoutout to @karpathy for his policy gradient code release. Within a couple of minutes Codex had the old dependencies updated and I was up and running!
4hViews 971Likes 3Bookmarks 6