Amii employs machine learning and artificial intelligence, together called machine intelligence, to meet a number of real-world and theoretical challenges, advancing academic understanding and solve the toughest of business problems.
In this post, we attempt to understand the principles that underlie the impressive performance of Deep Q-Networks (DQN) algorithm, demonstrated through the Arcade Learning Environment (ALE), and better contextualize its success.
Representation learning and option discovery are two of the biggest challenges in reinforcement learning (RL). Proto-RL is a well known approach for representation learning in MDPs. The representations learned with this framework are called proto-value functions (PVFs). In this paper we address the option discovery problem by showing how PVFs implicitly define options.