A toy AC Network built with curiosity through intrinsic reward, inspired by paper "Curiosity-driven Exploration by Self-supervised Prediction" (Deepak Pathak, Pulkit Agrawal, Alexei A. Efros, Trevor Darrell, 2017)
Medium Post: https://medium.com/@skelneko/curious-actor-critic-network-34526803d6bd
References: Playing Atari with Deep Reinforcement Learning https://arxiv.org/abs/1312.5602
Asynchronous Methods for Deep Reinforcement Learning https://arxiv.org/abs/1602.01783
Curiosity-driven Exploration by Self-supervised Prediction https://arxiv.org/abs/1705.05363