Crawling in Rogue's Dungeons With Deep Reinforcement Techniques

Abstract

This paper is a report of our extensive experimentation, during the last two years, of deep reinforcement techniques for training an agent to move in the dungeons of the famous Rogue video game. The challenging nature of the problem is tightly related to the procedural, random generation of new dungeon maps at each level, which forbids any form of level-specific learning and forces us to address the navigation problem in its full generality. Other interesting aspects of the game from the point of view of automatic learning are the par Show more