Curiosity Lab

Background:

• Reinforcement learning: Sutton and Barto

• Neural Network: Lippmann

• MDP, Information: Tishby and Polani

 

Curiosity Loop (Gordon)

1. Neural Networks, 2012 --> section 2.

2. J. of Comp. Neuro. Science, 2014 --> sections 3-4.

 

Hierarchical learning (Gordon)

1. ERLARS 2011

2. J. of Comp. Neuro. Science, 2014