mlsanityData to 7 Oct 2026

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

arXiv 2109.13202 ↗First posted 27 Sep 2021cs.LG stat.MLcited by 96

Not on the map. Why?

Abstract (arXiv)

Progress in deep reinforcement learning (RL) is heavily driven by the availability of challenging benchmarks used for training agents. However, benchmarks that are widely adopted by the community are not explicitly designed for evaluating specific capabilities of RL methods. While there exist environments for assessing particular open problems in RL (such as exploration, transfer learning, unsupervised environment design, or even language-assisted RL), it is generally difficult to extend these to richer, more complex environments once research goes beyond proof-of-concept results. We present MiniHack, a powerful sandbox framework for easily designing novel RL environments. MiniHack is a one-stop shop for RL experiments with environments ranging from small rooms to complex, procedurally generated worlds. By leveraging the full set of entities and environment dynamics from NetHack, one of the richest grid-based video games, MiniHack allows designing custom RL testbeds that are fast and convenient to use. With this sandbox framework, novel environments can be designed easily, either using a human-readable description language or a simple Python interface. In addition to a variety of RL tasks and baselines, MiniHack can wrap existing RL benchmarks and provide ways to seamlessly add additional complexity.

Key facts. Cited by 96 papers in the map (data through 7 Oct 2026). Builds on 38 of its 68 references that are in the map. First posted on arXiv 27 Sep 2021.

Builds on

38 of 68 references.

References · 38

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  3. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  4. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  5. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
  6. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  7. 2015Prioritized Experience Replaycited by 1,070
  8. 2018Exploration by Random Network Distillationcited by 966
  9. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 866
  10. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 769
  11. 2017Deep Reinforcement Learning that Matterscited by 727
  12. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 632
26 more
  1. 2016Deep Exploration via Bootstrapped DQNcited by 518
  2. 2017Ray: A Distributed Framework for Emerging AI Applicationscited by 516
  3. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478
  4. 2020Agent57: Outperforming the Atari Human Benchmarkcited by 300
  5. 2017StarCraft II: A New Challenge for Reinforcement Learningcited by 268
  6. 2020Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Designcited by 260
  7. 2019Go-Explore: a New Approach for Hard-Exploration Problemscited by 207
  8. 2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 201
  9. 2020The NetHack Learning Environmentcited by 196
  10. 2016ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learningcited by 178
  11. 2020RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environmentscited by 135
  12. 2019Behaviour Suite for Reinforcement Learningcited by 129
  13. 2020An empirical investigation of the challenges of real-world reinforcement learningcited by 75
  14. 2019An investigation of model-free planningcited by 64
  15. 2018Gotta Learn Fast: A New Benchmark for Generalization in RLcited by 59
  16. 2021On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learningcited by 59
  17. 2019Obstacle Tower: A Generalization Challenge in Vision, Control, and Planningcited by 54
  18. 2019Environmental drivers of systematicity and generalization in a situated agentcited by 50
  19. 2021Adversarially Guided Actor-Criticcited by 47
  20. 2018General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithmscited by 45
  21. 2019TorchBeast: A PyTorch Platform for Distributed RLcited by 41
  22. 2021The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priorscited by 40
  23. 2020BeBold: Exploration Beyond the Boundary of Explored Regionscited by 32
  24. 2020Griddly: A platform for AI research in gamescited by 31
  25. 2019Rogue-Gym: A New Challenge for Generalization in Reinforcement Learningcited by 6
  26. 2017Exploration in NetHack With Secret Discoverycited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 22; 2023: 18; 2024: 18; 2025: 18; 2026: 15.

96 papers.

Sort:

By area:

  1. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  2. 2022Evolving Curricula with Regret-Based Environment Designcited by 166
  3. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
  4. 2024BALROG: Benchmarking Agentic LLM and VLM Reasoning On Gamescited by 141
  5. 2023Human-Timescale Adaptation in an Open-Ended Task Spacecited by 136
  6. 2022SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learningcited by 118
  7. 2023Motif: Intrinsic Motivation from Artificial Intelligence Feedbackcited by 99
  8. 2024DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agentscited by 89
  9. 2024Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learningcited by 80
  10. 2022Automated Reinforcement Learning (AutoRL): A Survey and Open Problemscited by 69
  11. 2022A Generalist Neural Algorithmic Learnercited by 58
  12. 2022Exploration via Elliptical Episodic Bonusescited by 51
38 more
  1. 2022Improving Intrinsic Exploration with Language Abstractionscited by 49
  2. 2022Contextualize Me -- The Case for Context in Reinforcement Learningcited by 41
  3. 2023Generalization to New Sequential Decision Making Tasks with In-Context Learningcited by 39
  4. 2021CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agentscited by 36
  5. 2025Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learningcited by 34
  6. 2023The Generalization Gap in Offline Reinforcement Learningcited by 25
  7. 2024Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skillscited by 24
  8. 2021CARL: A Benchmark for Contextual and Adaptive Reinforcement Learningcited by 21
  9. 2022Mind the gap: Challenges of deep learning approaches to Theory of Mindcited by 21
  10. 2022Insights From the NeurIPS 2021 NetHack Challengecited by 20
  11. 2022General Intelligence Requires Rethinking Explorationcited by 20
  12. 2024Retrieval-Augmented Decision Transformer: External Memory for In-context RLcited by 20
  13. 2023A Study of Global and Episodic Bonuses for Exploration in Contextual MDPscited by 19
  14. 2024Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learningcited by 18
  15. 2022Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worldscited by 17
  16. 2024Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agentscited by 17
  17. 2024DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraftcited by 17
  18. 2022Grounding Aleatoric Uncertainty for Unsupervised Environment Designcited by 16
  19. 2022Dungeons and Data: A Large-Scale NetHack Datasetcited by 16
  20. 2022The Effectiveness of World Models for Continual Reinforcement Learningcited by 15
  21. 2023A Domain-Agnostic Approach for Characterization of Lifelong Learning Systemscited by 13
  22. 2021SILG: The Multi-environment Symbolic Interactive Language Grounding Benchmarkcited by 10
  23. 2021Situated Dialogue Learning through Procedural Environment Generationcited by 9
  24. 2022IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agentscited by 9
  25. 2023Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actorscited by 9
  26. 2023LLM Augmented Hierarchical Agentscited by 9
  27. 2024Enhancing Agent Learning through World Dynamics Modelingcited by 9
  28. 2025SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Modelscited by 9
  29. 2025The impact of intrinsic rewards on exploration in Reinforcement Learningcited by 8
  30. 2022Hierarchical Kickstarting for Skill Transfer in Reinforcement Learningcited by 7
  31. 2023Composing Task Knowledge with Modular Successor Feature Approximatorscited by 7
  32. 2023Improving Intrinsic Exploration by Creating Stationary Objectivescited by 7
  33. 2024Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RLcited by 7
  34. 2025Benchmarking World-Model Learning with Environment-Level Queriescited by 7
  35. 2022L2Explorer: A Lifelong Reinforcement Learning Assessment Environmentcited by 6
  36. 2022Powderworld: A Platform for Understanding Generalization via Rich Task Distributionscited by 6
  37. 2024IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learningcited by 6
  38. 2025Scalable Option Learning in High-Throughput Environmentscited by 5

50 most cited of 96 All 96 (JSON)