Montezuma's Revenge

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

1 leaderboard table shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

1 dataset whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 31 papers with code (61 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Rainbow: Combining Improvements in Deep Reinforcement Learning
  6 Oct 2017 34 repositories listed Syntology ran 2 of 6 samples · 4 unverified · 1 pointer-only (licence)
  The deep reinforcement learning community has made several independent improvements to the DQN algorithm.
• Exploration by Random Network Distillation
  30 Oct 2018 22 repositories listed Syntology ran 26 of 43 samples · 17 unverified · 15 pointer-only (licence)
  In particular we establish state of the art performance on Montezuma's Revenge, a game famously difficult for deep reinforcement learning methods.
• Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
  20 Apr 2016 4 repositories listed
  Learning goal-directed behavior in environments with sparse feedback is a major challenge for reinforcement learning algorithms.
• Go-Explore: a New Approach for Hard-Exploration Problems
  30 Jan 2019 3 repositories listed Syntology ran 2 of 4 samples · 2 unverified · 4 pointer-only (licence)
  Go-Explore can also harness human-provided domain knowledge and, when augmented with it, scores a mean of over 650k points on Montezuma's Revenge.
• A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs
  5 Jun 2023 2 repositories listed
  This results in an algorithm which sets a new state of the art across 16 tasks from the MiniHack suite used in prior work, and also performs robustly on Habitat and Montezuma's Revenge.
• Reinforcement Learning with Latent Flow
  6 Jan 2021 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  Temporal information is essential to learning effective policies with Reinforcement Learning (RL).
• First return, then explore
  27 Apr 2020 2 repositories listed Syntology ran 2 of 4 samples · 2 unverified · 4 pointer-only (licence)
  The promise of reinforcement learning is to solve complex sequential decision problems autonomously by specifying a high-level reward function only.
• Exploring Unknown States with Action Balance
  10 Mar 2020 2 repositories listed
  In this paper, we focus on improving the effectiveness of finding unknown states and propose action balance exploration, which balances the frequency of selecting each action at a given state and can be treated as an…
• Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks
  6 Oct 2018 2 repositories listed
  Being able to reach any desired location in the environment can be a valuable asset for an agent.
• PoE-World: Compositional World Modeling with Products of Programmatic Experts
  16 May 2025 1 repository listed
  Learning how the world works is central to building AI agents that can adapt to complex environments.
• A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
  29 May 2024 1 repository listed Syntology ran 7 of 11 samples · 4 unverified · 11 pointer-only (licence)
  Continual learning with deep neural networks presents challenges distinct from both the fixed-dataset and convex continual learning regimes.
• Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
  5 Feb 2024 1 repository listed
  Fine-tuning is a widespread technique that allows practitioners to transfer pre-trained capabilities, as recently showcased by the successful applications of foundation models.
• Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning
  5 Jun 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  We propose a new method for count-based exploration in high-dimensional state spaces.
• Redeeming Intrinsic Rewards via Constrained Optimization
  14 Nov 2022 1 repository listed Syntology ran 0 of 4 samples · 4 unverified
  However, on easy exploration tasks, the agent gets distracted by intrinsic rewards and performs unnecessary exploration even when sufficient task (also called extrinsic) reward is available.
• Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient
  13 Oct 2022 1 repository listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  We consider a hybrid reinforcement learning setting (Hybrid RL), in which an agent has access to an offline dataset and the ability to collect experience via real-world online interaction.
• Cell-Free Latent Go-Explore
  31 Aug 2022 1 repository listed
  In this paper, we introduce Latent Go-Explore (LGE), a simple and general approach based on the Go-Explore paradigm for exploration in reinforcement learning (RL).
• Open-Ended Reinforcement Learning with Neural Reward Functions
  16 Feb 2022 1 repository listed
  Inspired by the great success of unsupervised learning in Computer Vision and Natural Language Processing, the Reinforcement Learning community has recently started to focus more on unsupervised discovery of skills.
• NovelD: A Simple yet Effective Exploration Criterion
  1 Dec 2021 1 repository listed
  We analyze NovelD thoroughly in MiniGrid and found that empirically it helps the agent explore the environment more uniformly with a focus on exploring beyond the boundary.
• Learning Abstract Models for Strategic Exploration and Fast Reward Transfer
  12 Jul 2020 1 repository listed
  Model-based reinforcement learning (RL) is appealing because (i) it enables planning and thus more strategic exploration, and (ii) by decoupling dynamics from rewards, it enables fast transfer to new reward functions.
• Uncertainty-sensitive Learning and Planning with Ensembles
  19 Dec 2019 1 repository listed
  The former manifests itself through the use of value function, while the latter is powered by a tree search planner.
• DeepSynth: Automata Synthesis for Automatic Task Segmentation in Deep Reinforcement Learning
  22 Nov 2019 1 repository listed
  This paper proposes DeepSynth, a method for effective training of deep Reinforcement Learning (RL) agents when the reward is sparse and non-Markovian, but at the same time progress towards the reward requires achieving…
• Uncertainty - sensitive learning and planning with ensembles
  25 Sep 2019 1 repository listed
  Notably, our method performs well in environments with sparse rewards where standard TD(1) backups fail.
• Combining Experience Replay with Exploration by Random Network Distillation
  18 May 2019 1 repository listed
  Our work is a simple extension of the paper "Exploration by Random Network Distillation".
• Using Natural Language for Reward Shaping in Reinforcement Learning
  5 Mar 2019 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  A common approach to reduce interaction time with the environment is to use reward shaping, which involves carefully designing reward functions that provide the agent intermediate rewards for progress towards the goal.
• Empowerment-driven Exploration using Mutual Information Estimation
  11 Oct 2018 1 repository listed
  However, many of the state of the art deep reinforcement learning algorithms, that rely on epsilon-greedy, fail on these environments.
• Playing hard exploration games by watching YouTube
  29 May 2018 1 repository listed Syntology ran 0 of 3 samples · 3 unverified
  One successful method of guiding exploration in these domains is to imitate trajectories provided by a human demonstrator.
• Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning
  18 May 2017 1 repository listed
  We highlight the advantage of our approach in one of the hardest games -- Montezuma's revenge -- for which the ability to handle sparse rewards is key.
• Beating Atari with Natural Language Guided Reinforcement Learning
  18 Apr 2017 1 repository listed
  We introduce the first deep reinforcement learning agent that learns to beat Atari games with the aid of natural language instructions.
• Count-Based Exploration with Neural Density Models
  3 Mar 2017 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  This pseudo-count was used to generate an exploration bonus for a DQN agent and combined with a mixed Monte Carlo update was sufficient to achieve state of the art on the Atari 2600 game Montezuma's Revenge.
• Playing Atari Games with Deep Reinforcement Learning and Human Checkpoint Replay
  18 Jul 2016 1 repository listed
  This paper introduces a novel method for learning how to play the most difficult Atari 2600 games from the Arcade Learning Environment using deep reinforcement learning.

Syntology lines on 12 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.