Comment Comment by Hydraulix989 What is state of the art in reinforcement learning right now?https://arxiv.org/abs/1602.01783Is there a way to deal with "sparse" training data (state, action, reward) triples -- sparse in "state"? parent Hydraulix989 10 years ago
https://arxiv.org/abs/1602.01783
Is there a way to deal with "sparse" training data (state, action, reward) triples -- sparse in "state"?