Deep Reinforcement Learning and the Deadly Triad — mentioned by ArtWomb

Fri, 26 Apr 2019 01:11:34 GMT

>>> There is a large number of fancy bayesian hyper-parameter optimization toolboxes around and a few of my friends have also reported success with them, but my personal experience is that the state of the art approach to exploring a nice and wide space of models and hyperparameters is to use an intern :). Just kidding. LOL. Human assisted training at scale is perfectly allowable for mission critical success. Especially if you enjoy an unlimited research budget! You can follow these instructions to the letter. And the same problems around generalization will arise. It's foundational. For…

Paper and discussion history. A mention is not an endorsement.

Deep Reinforcement Learning and the Deadly Triad · HackerPapers discussions

Deep Reinforcement Learning and the Deadly Triad — mentioned by ArtWomb