Playing Montezumas Revenge with Intrinsic Motivation

This is a short video showcasing the paper Unifying CountBased Exploration and Intrinsic Motivation by Bellemare, Srinivasan, Ostrovski, Schaul, Saxton, and Munos from Google DeepMind. The video depicts a DQN agent playing Montezuma s Revenge via the Arcade Learning Environment. The agent s reward function is augmented with an intrinsic reward based on a pseudocount, itself computed from a sequential density model. This intrinsic reward allows the agent to explore a ful