RL + LLM + tools + hooks +
Skills.
and then go optimize over the space idk. maximize +r relative to each action a_n you take, at each state s_n (x1-xn)
Every time you do a_n… we arrive at state s’ with reward +/- r.
Maximize Reward.
Wait define it first…
RL + LLM + tools + hooks +
Skills.
and then go optimize over the space idk. maximize +r relative to each action a_n you take, at each state s_n (x1-xn)
Every time you do a_n… we arrive at state s’ with reward +/- r.
Maximize Reward.
Wait define it first…
@DrDavidJoyner
@https://scholar.google.com/citations?user=yVO_HIIAAAAJ&hl=en
"How would you modify UT Austin's Graudate CS Curriculum?"
- an outgoing student
RL is a puzzle! we are the pieces?
This is almost life intuitively, and the anthropic principle.
but real fruitful life is without illness and rarely in disease! This isn’t homeostasis surely?
nature has tuned itself for us, we should situate our expertise for more…