Yann LeCun
@ylecun
Professor at NYU. Chief AI Scientist at Meta.
Researcher in AI, Machine Learning, Robotics, etc.
ACM Turing Award Laureate.
17-06-2009 16:05:51
19,0K Tweets
712,0K Followers
719 Following
Active Inference Institute Finding the best sequence of actions that minimize an objective function (an energy) measured over the predicted trajectory is very much like inferring latent variables.
If you insist on being Bayesian, then you infer a distribution over action sequences by trading the average