Sarah Dean PRO
asst prof in CS at Cornell
Prof. Sarah Dean
MW 2:55-4:10pm
255 Olin Hall
action
state
\(a_t\)
reward
\(s_t\)
\(r_t\)
action \(a_t\)
state \(s_t\)
reward \(r_t\)
Control feedback
policy \(\pi\)
transitions \(P,f\)
action \(a_t\)
state \(s_t\)
reward \(r_t\)
policy
data \((s_t,a_t,r_t)\)
policy \(\pi\)
transitions \(P,f\)
experience
Data feedback
action \(a_t\)
state \(s_t\)
reward \(r_t\)
policy
data \((s_t,a_t,r_t)\)
policy \(\pi\)
transitions \(P,f\)
experience
unknown in Unit 2
predictor
data
PollEV
PSet 4, Unit 3
next week
next week
two weeks
By Sarah Dean