36 citations · 59 across the 5 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.AI2019★ 12 cited
Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions
Juergen Schmidhuber
We transform reinforcement learning (RL) into a form of supervised learning (SL) by turning traditional RL on its head, calling this Upside Down RL (UDRL). Standard RL predicts rew…
cs.NE2019★ 3 cited
Generative Adversarial Networks are Special Cases of Artificial Curiosity (1990) and also Closely Related to Predictability Minimization (1991)
Juergen Schmidhuber
I review unsupervised or self-supervised neural networks playing minimax games in game-theoretic settings: (i) Artificial Curiosity (AC, 1990) is based on two such networks. One ne…