Skip to content
Global sound
Mechanical Dreams

Mechanical Dreams

Learning beyond Teacher

· 21 min

Show notes

In this episode:
• Distillation vs. Reinforcement Learning: Linda and Norris introduce the paper and discuss the differences between off-policy and on-policy distillation.
• The Math Behind the Magic: The hosts dive into the mathematical equivalence between on-policy distillation and KL-constrained dense RL.
• Extrapolating the Reward: Linda introduces Generalized OPD and the concept of reward extrapolation by setting the scaling factor above 1.
• Merging Experts and Reward Correction: They discuss merging multiple domain teachers and the strong-to-weak distillation setting, including the…

Website: mechanicaldreams.mechanicaldirk.com

Live, last hour: 7,539 songs on 3,092 stations in 126 countries

Discover the world through radio

More ways to discover (9)

Heard something good? Save it, or open it straight away in Spotify.

Radio SigmaContinue listening