PSYCH 7A Lecture Notes - Lecture 13: Reinforcement Learning, Operant Conditioning
19
PSYCH 7A Full Course Notes
Verified Note
19 documents
Document Summary
Behaviors are reinforced every time they happen. So basically every time your pupper does a trick you give him a treat *what a good boy * Continuous reinforcement learning happens rapidly, but so does extinction. Only reinforce some responses: like you give your pupper treats sometimes. More resistant to extinction takes longer to go extinct. 4 diff schedules: : fixed-ratio: reinforce behavior after a set # of responses. Give the pigeon a treat after every 10th trick 1 out of. The faster the bird does the trick the faster he gets the trick: variable-ratio: reinforced after an unpredictable # of responses. So basically fixed ratio but more random. In operant conditioning, a variable-ratio schedule is a schedule of reinforcement where a response is reinforced after an unpredictable number of responses. This schedule creates a steady, high rate of responding. : fixed-interval: reinforce the 1st response after a fixed time period.
