Browse > Playing Games > Atari Games > Montezuma's Revenge

Montezuma's Revenge

5 papers with code · Playing Games
Subtask of Atari Games

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.

State-of-the-art leaderboards

No evaluation results yet. Help compare methods by submit evaluation metrics.

Latest papers without code

Escape Room: A Configurable Testbed for Hierarchical Reinforcement Learning

22 Dec 2018Jacob Menashe et al

We show that the ERD presents a suite of challenges with scalable difficulty to provide a smooth learning gradient from Taxi to the Arcade Learning Environment.

HIERARCHICAL REINFORCEMENT LEARNING MONTEZUMA'S REVENGE

22 Dec 2018

Learning Montezuma's Revenge from a Single Demonstration

8 Dec 2018Tim Salimans et al

We propose a new method for learning from a single demonstration to solve hard exploration tasks like the Atari game Montezuma's Revenge.

MONTEZUMA'S REVENGE

08 Dec 2018

Contingency-Aware Exploration in Reinforcement Learning

ICLR 2019 Jongwook Choi et al

This paper investigates whether learning contingency-awareness and controllable aspects of an environment can lead to better exploration in reinforcement learning.

MONTEZUMA'S REVENGE

05 Nov 2018

Learning Representations in Model-Free Hierarchical Reinforcement Learning

23 Oct 2018Jacob Rafati et al

When combined with an intrinsic motivation learning mechanism, this method learns subgoals and skills together, based on experiences in the environment.

HIERARCHICAL REINFORCEMENT LEARNING MONTEZUMA'S REVENGE

23 Oct 2018

Deep Curiosity Search: Intra-Life Exploration Can Improve Performance on Challenging Deep Reinforcement Learning Problems

1 Jun 2018Christopher Stanton et al

The strong performance of DeepCS on these sparse- and dense-reward tasks suggests that encouraging intra-life novelty is an interesting, new approach for improving performance in Deep RL and motivates further research into hybridizing across-training and intra-life exploration methods.

MONTEZUMA'S REVENGE

01 Jun 2018

Observe and Look Further: Achieving Consistent Performance on Atari

29 May 2018Tobias Pohlen et al

Despite significant advances in the field of deep Reinforcement Learning (RL), today's algorithms still fail to learn human-level policies consistently over a set of diverse tasks such as Atari 2600 games.

MONTEZUMA'S REVENGE

29 May 2018

Hierarchical Imitation and Reinforcement Learning

ICML 2018 Hoang M. Le et al

We study how to effectively leverage expert feedback to learn sequential decision-making policies.

DECISION MAKING IMITATION LEARNING MONTEZUMA'S REVENGE

01 Mar 2018

Learning High-level Representations from Demonstrations

19 Feb 2018Garrett Andersen et al

A common approach to HL, is to provide the agent with a number of high-level skills that solve small parts of the overall problem.

MONTEZUMA'S REVENGE

19 Feb 2018

Exploration in Feature Space for Reinforcement Learning

5 Oct 2017Suraj Narayanan Sasikumar

Function approximation techniques enable RL agents to generalize in order to estimate the value of unvisited states, but at present few methods have achieved generalization about the agent's uncertainty regarding unvisited states.

MONTEZUMA'S REVENGE

05 Oct 2017

Deep Abstract Q-Networks

2 Oct 2017Melrose Roderick et al

We examine the problem of learning and planning on high-dimensional domains with long horizons and sparse rewards.

MONTEZUMA'S REVENGE

02 Oct 2017