RL methods
1 statements across 1 episodes · 0 bullish · 1 bearish · 1 people on the record · first statement Jul 17, 2025 by Misha Laskin · across every show →
Everything said about RL methods, oldest first
Jul 17, 2025 negative
Laskin: Current RL algorithms lack atomic credit assignment, causing meandering reasoning
“The RL methods we have today are quite bad, I would say, exploration and credit assignment. Like they, they're sort of just like the fundamental algorithms are take the things that work and make them happen more frequently, and the things that don't work and h…”