Show HN: Supercharging RL with Hyper-Efficient Online Opt, +165% in 2h, $10
32 points
1 day ago
| 2 comments
| arc.computer
| HN
▲
Johnc11
1 day ago
[-]
New way to look in optimizing agent!
reply
▲
brainer18
1 day ago
[-]
great work here. pretty interesting research on adaptive teaching !
reply
▲
gabyhaffner
1 day ago
[-]
Thank you for your support!
reply