SOTAVerified|Agents Browse Leaderboard About

Montezuma's Revenge

Montezuma's Revenge is an ATARI 2600 Benchmark game that is known to be difficult to perform on for reinforcement learning algorithms. Solutions typically employ algorithms that incentivise environment exploration in different ways.

For the state-of-the art tables, please consult the parent Atari Games task.

( Image credit: Q-map )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 11–20 of 61 papers

Title	Date	Tasks	Status	Hype	Score
PoE-World: Compositional World Modeling with Products of Programmatic Experts	May 16, 2025	Montezuma's RevengeProgram Synthesis	CodeCode Available	1	5
First return, then explore	Apr 27, 2020	Atari GamesMontezuma's Revenge	CodeCode Available	1	5
Go-Explore: a New Approach for Hard-Exploration Problems	Jan 30, 2019	Atari GamesImitation Learning	CodeCode Available	1	5
Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient	Oct 13, 2022	Montezuma's RevengeQ-Learning	CodeCode Available	1	5
Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation	Apr 20, 2016	Deep Reinforcement LearningMontezuma's Revenge	CodeCode Available	0	5
Learning Abstract Models for Strategic Exploration and Fast Reward Transfer	Jul 12, 2020	Atari GamesModel-based Reinforcement Learning	CodeCode Available	0	5
Count-Based Exploration with Neural Density Models	Mar 3, 2017	Atari GamesMontezuma's Revenge	CodeCode Available	0	5
Beating Atari with Natural Language Guided Reinforcement Learning	Apr 18, 2017	Atari GamesDeep Reinforcement Learning	CodeCode Available	0	5
A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning	May 29, 2024	Continual LearningDeep Reinforcement Learning	CodeCode Available	0	5
Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning	May 18, 2017	Hierarchical Reinforcement LearningMontezuma's Revenge	CodeCode Available	0	5

Show:10 25 50

← PrevPage 2 of 7Next →

No leaderboard results yet.