Crawling in Rogue's dungeons with (partitioned) A3C
Asperti, Andrea, Cortesi, Daniele, Sovrano, Francesco
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.
Apr-29-2018
- Country:
- North America > Canada (0.68)
- Genre:
- Research Report (0.84)
- Industry:
- Leisure & Entertainment > Games > Computer Games (0.48)
- Technology: