'Robust Black-Box Optimization for Stochastic Search and Episodic Reinforcement Learning', by Maximilian Hüttenrauch, Gerhard Neumann.

http://jmlr.org/papers/v25/22-0564.html

#reinforcement #optimizers #optimizes

My buddy Sichu and I have begun work on a #P2P #didactic #protocol; an #open, #emergent #knowledge #engine for our #species. Clearly we are not the first to #work on this, but we are taking an approach which #sets our #project apart from all the #rest. We are putting #collaborative #teaching and #learning at the center of the #autopoetic "main #loop " of the #thing, so it #dynamically #optimizes for #reflectivity. Looking for others #interested in getting #involved!