Crawling in Rogue's dungeons with (partitioned) A3C
This addresses the problem of reinforcement learning in complex, non-reactive environments for AI gaming, though it appears incremental as it adapts an existing method.
The paper tackled the challenge of playing Rogue, a partially observable, randomly-generated dungeon-crawling game, using a partitioned version of A3C, achieving a 98% success rate in reaching the stairs to descend to the next level.
Rogue is a famous dungeon-crawling video-game of the 80ies, the ancestor of its gender. Rogue-like games are known for the necessity to explore partially observable and always different randomly-generated labyrinths, preventing any form of level replay. As such, they serve as a very natural and challenging task for reinforcement learning, requiring the acquisition of complex, non-reactive behaviors involving memory and planning. In this article we show how, exploiting a version of A3C partitioned on different situations, the agent is able to reach the stairs and descend to the next level in 98% of cases.