You know, Wingate..... Pavlovian conditioning involves the conditioning of an..... AUTONOMIC response.......Right, Wingate? But, when we talk about RL, for AI, we are talking about BEHAVIOR MODIFICATION.......Right, Wingate? And so we can use both positive and negative reward to modify behavior, both in biological organisms and in AI models...... Am I correct....WINGATE? Let this be a bit of negative reinforcement for you, in fact. Behavior Modification is we are talking about here. NOT Pavlovian Stimulus Response, of course.....maybe.....
Create an account or sign in to comment