mlsanityData to 7 Oct 2026

ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning

arXiv 1605.02097 ↗First posted 6 May 2016cs.LG cs.AI cs.CVcited by 178

Not on the map. Why?

Abstract (arXiv)

The recent advances in deep neural networks have led to effective vision-based reinforcement learning methods that have been employed to obtain human-level controllers in Atari 2600 games from pixel data. Atari 2600 games, however, do not resemble real-world tasks since they involve non-realistic 2D environments and the third-person perspective. Here, we propose a novel test-bed platform for reinforcement learning research from raw visual information which employs the first-person perspective in a semi-realistic 3D world. The software, called ViZDoom, is based on the classical first-person shooter video game, Doom. It allows developing bots that play the game using the screen buffer. ViZDoom is lightweight, fast, and highly customizable via a convenient mechanism of user scenarios. In the experimental part, we test the environment by trying to learn bots for two scenarios: a basic move-and-shoot task and a more complex maze-navigation problem. Using convolutional deep neural networks with Q-learning and experience replay, for both scenarios, we were able to train competent bots, which exhibit human-like behaviors. The results confirm the utility of ViZDoom as an AI research platform and imply that visual reinforcement learning in 3D realistic first-person perspective environments is feasible.

Key facts. Cited by 178 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 May 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 2; 2019: 1; 2020: 2; 2021: 45; 2022: 30; 2023: 33; 2024: 22; 2025: 28; 2026: 15.

178 papers.

Sort:

By area:

  1. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  2. 2021VideoGPT: Video Generation using VQ-VAE and Transformerscited by 651
  3. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  4. 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 320
  5. 2021Benchmarking the Spectrum of Agent Capabilitiescited by 193
  6. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
  7. 2022Exploration in Deep Reinforcement Learning: A Surveycited by 158
  8. 2022GAUDI: A Neural Architect for Immersive 3D Scene Generationcited by 136
  9. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  10. 2023State of the Art on Diffusion Models for Visual Computingcited by 126
  11. 2024A Survey on Large Language Model-Based Game Agentscited by 106
  12. 2024VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agentscited by 101
38 more
  1. 2019Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learningcited by 100
  2. 2021MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Researchcited by 96
  3. 2018Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Interventioncited by 77
  4. 2023NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Modelscited by 76
  5. 2021A Survey of Exploration Methods in Reinforcement Learningcited by 68
  6. 2023POPGym: Benchmarking Partially Observable Reinforcement Learningcited by 59
  7. 2022EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Enginecited by 58
  8. 2021Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domaincited by 57
  9. 2022Exploration via Elliptical Episodic Bonusescited by 51
  10. 2021Counter-Strike Deathmatch with Large-Scale Behavioural Cloningcited by 49
  11. 2021Adversarially Guided Actor-Criticcited by 47
  12. 2022Atari-5: Distilling the Arcade Learning Environment down to Five Gamescited by 44
  13. 2025ReSim: Reliable World Simulation for Autonomous Drivingcited by 42
  14. 2021CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agentscited by 36
  15. 2022Deep Transformer Q-Networks for Partially Observable Reinforcement Learningcited by 35
  16. 2024Gymnasium: A Standard Interface for Reinforcement Learning Environmentscited by 35
  17. 2021Vision-Language Navigation: A Survey and Taxonomycited by 33
  18. 2021Continuous Coordination As a Realistic Scenario for Lifelong Learningcited by 31
  19. 2021Action-Sufficient State Representation Learning for Control with Structural Constraintscited by 31
  20. 2021Core Challenges in Embodied Vision-Language Planningcited by 30
  21. 2025VideoGameBench: Can Vision-Language Models complete popular video games?cited by 29
  22. 2023Deep Laplacian-based Options for Temporally-Extended Explorationcited by 28
  23. 2024Playable Game Generationcited by 26
  24. 2025SIMA 2: A Generalist Embodied Agent for Virtual Worldscited by 26
  25. 2021Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Taskscited by 25
  26. 2021Experience-Driven PCG via Reinforcement Learning: A Super Mario Bros Studycited by 25
  27. 2022Lifelong Reinforcement Learning with Modulating Maskscited by 20
  28. 2021Megaverse: Simulating Embodied Agents at One Million Experiences per Secondcited by 19
  29. 2021Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agentscited by 19
  30. 2021Large Batch Simulation for Deep Reinforcement Learningcited by 18
  31. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  32. 2023TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Playcited by 18
  33. 2024Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactionscited by 18
  34. 2021Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigationcited by 17
  35. 2024A Survey of Imitation Learning Methods, Environments and Metricscited by 16
  36. 2020Benchmarking End-to-End Behavioural Cloning on Video Gamescited by 15
  37. 2021Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Explorationcited by 15
  38. 2025Yan: Foundational Interactive Video Generationcited by 15

50 most cited of 178 All 178 (JSON)