Radhika Gaonkar(@GaonkarRadhika):Excited to be presenting at Ray Summit today! I ran a bunch of experiments digging into reward hacking and strange verifier behaviors that crop up in long-horizon RL training. There’s been a lot of interesting work in this space, and my talk will cover a framework to stress-test these behaviors before you scale your training runs. Come say hi if you're around! All built on @PrimeIntellect’s stack!

Radhika Gaonkar

@GaonkarRadhika

Applied Research @primeintellect | ex-Microsoft

加入 July 2019

1.3K 正在关注 486 粉丝

Radhika Gaonkar@GaonkarRadhika

2026.08.26 17:13

Excited to be presenting at Ray Summit today! I ran a bunch of experiments digging into reward hacking and strange verifier behaviors that crop up in long-horizon RL training. There’s been a lot of interesting work in this space, and my talk will cover a framework to stress-test these behaviors before you scale your training runs. Come say hi if you're around! All built on @PrimeIntellect’s stack!

显示更多