# MontezumaRevenge-v0

Maximize your score in the Atari 2600 game MontezumaRevenge. In this environment, the observation is an RGB image of the screen, which is an array of shape (210, 160, 3) Each action is repeatedly performed for a duration of \(k\) frames, where \(k\) is uniformly sampled from \(\{2, 3, 4\}\).

## MontezumaRevenge-v0 Evaluations

Algorithm | Best 100-episode performance | Submitted |
---|---|---|

pkumusic's algorithm writeup | 2500.00 ± 0.00 | |

pkumusic's algorithm writeup | 2440.00 ± 37.91 | |

Itsukara's algorithm writeup | 1284.00 ± 36.91 | |

Itsukara's algorithm writeup | 1127.00 ± 53.19 | |

Itsukara's algorithm writeup | 448.00 ± 27.60 | |

pkumusic's algorithm writeup | 129.00 ± 30.20 | |

gdb's algorithm writeup | 0.00 ± 0.00 | |

steveKapturowski's algorithm | 396.00 ± 4.42 | |

ceobillionaire's algorithm | 1.00 ± 1.11 | |

gdb's algorithm | 1.00 ± 1.11 | |

gdb's algorithm random baseline | 1.00 ± 1.11 | |

basarane's algorithm | 0.00 ± 0.00 | |

justheuristic's algorithm | 0.00 ± 0.00 |