Playing SNES in the Retro Learning Environment

7 Nov 2016  ·  Nadav Bhonker, Shai Rozenberg, Itay Hubara ·

Mastering a video game requires skill, tactics and strategy. While these attributes may be acquired naturally by human players, teaching them to a computer program is a far more challenging task. In recent years, extensive research was carried out in the field of reinforcement learning and numerous algorithms were introduced, aiming to learn how to perform human tasks such as playing video games. As a result, the Arcade Learning Environment (ALE) (Bellemare et al., 2013) has become a commonly used benchmark environment allowing algorithms to train on various Atari 2600 games. In many games the state-of-the-art algorithms outperform humans. In this paper we introduce a new learning environment, the Retro Learning Environment --- RLE, that can run games on the Super Nintendo Entertainment System (SNES), Sega Genesis and several other gaming consoles. The environment is expandable, allowing for more video games and consoles to be easily added to the environment, while maintaining the same interface as ALE. Moreover, RLE is compatible with Python and Torch. SNES games pose a significant challenge to current algorithms due to their higher level of complexity and versatility.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
SNES Games F-Zero Dueling D-DQN Score 5161 # 1
SNES Games F-Zero DQN Score 3116 # 3
SNES Games F-Zero D-DQN Score 3636 # 2
SNES Games Gradius III Dueling D-DQN Score 16929 # 1
SNES Games Gradius III DQN Score 7583 # 3
SNES Games Gradius III D-DQN Score 12343 # 2
SNES Games Mortal Kombat D-DQN Score 56200 # 3
SNES Games Mortal Kombat DQN Score 83733 # 2
SNES Games Mortal Kombat Dueling D-DQN Score 169300 # 1
SNES Games Super Mario Dueling D-DQN Score 20030 # 1
SNES Games Super Mario DQN Score 11765 # 3
SNES Games Super Mario D-DQN Score 16946 # 2
SNES Games Wolfenstein D-DQN Score 83 # 2
SNES Games Wolfenstein Dueling D-DQN Score 40 # 3
SNES Games Wolfenstein DQN Score 100 # 1

Methods


No methods listed for this paper. Add relevant methods here