# ViZDoom Competitions: Playing Doom from Pixels

arXiv: https://arxiv.org/abs/1809.03470 · HTML: https://mlsanity.com/paper/1809.03470/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2018.

## Built on by (most cited first, 30 of 51)

- [Diffusion Models Are Real-Time Game Engines](https://mlsanity.com/paper/2408.14837/) (2024)
- [Avalanche: an End-to-End Library for Continual Learning](https://mlsanity.com/paper/2104.00405/) (2021)
- [Counter-Strike Deathmatch with Large-Scale Behavioural Cloning](https://mlsanity.com/paper/2104.04258/) (2021)
- [Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents](https://mlsanity.com/paper/2102.02926/) (2021)
- [Facing Off World Model Backbones: RNNs, Transformers, and S4](https://mlsanity.com/paper/2307.02064/) (2023)
- [MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned](https://mlsanity.com/paper/2202.10583/) (2022)
- [Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents](https://mlsanity.com/paper/2510.23691/) (2025)
- [Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2111.09858/) (2021)
- [Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents](https://mlsanity.com/paper/2309.17207/) (2023)
- [MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines](https://mlsanity.com/paper/2603.06679/) (2026)
- [Benchmarking End-to-End Behavioural Cloning on Video Games](https://mlsanity.com/paper/2004.00981/) (2020)
- [Task-Induced Representation Learning](https://mlsanity.com/paper/2204.11827/) (2022)
- [Towards Principled Representation Learning from Videos for Reinforcement Learning](https://mlsanity.com/paper/2403.13765/) (2024)
- [A Comprehensive Review of Multi-Agent Reinforcement Learning in Video Games](https://mlsanity.com/paper/2509.03682/) (2025)
- [RaidEnv: Exploring New Challenges in Automated Content Balancing for Boss Raid Games](https://mlsanity.com/paper/2307.01676/) (2023)
- [Will GPT-4 Run DOOM?](https://mlsanity.com/paper/2403.05468/) (2024)
- [Graph augmented Deep Reinforcement Learning in the GameRLand3D environment](https://mlsanity.com/paper/2112.11731/) (2021)
- [BehAVE: Behaviour Alignment of Video Game Encodings](https://mlsanity.com/paper/2402.01335/) (2024)
- [A Behavior-Aware Approach for Deep Reinforcement Learning in Non-stationary Environments without Known Change Points](https://mlsanity.com/paper/2405.14214/) (2024)
- [Agents that Listen: High-Throughput Reinforcement Learning with Multiple Sensory Systems](https://mlsanity.com/paper/2107.02195/) (2021)
- [Godot Reinforcement Learning Agents](https://mlsanity.com/paper/2112.03636/) (2021)
- [Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?](https://mlsanity.com/paper/2202.12174/) (2022)
- [SMPL: Simulated Industrial Manufacturing and Process Control Learning Environments](https://mlsanity.com/paper/2206.08851/) (2022)
- [Lamarckian Platform: Pushing the Boundaries of Evolutionary Reinforcement Learning towards Asynchronous Commercial Games](https://mlsanity.com/paper/2209.10055/) (2022)
- [Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent Environments](https://mlsanity.com/paper/2407.03969/) (2024)
- [Distilling Reinforcement Learning Tricks for Video Games](https://mlsanity.com/paper/2107.00703/) (2021)
- [Tracking and Planning with Spatial World Models](https://mlsanity.com/paper/2201.10335/) (2022)
- [Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning](https://mlsanity.com/paper/2406.08404/) (2024)
- [Unified Distributed Environment](https://mlsanity.com/paper/2205.06946/) (2022)
- [Behavioural Cloning in VizDoom](https://mlsanity.com/paper/2401.03993/) (2024)

## Abstract (arXiv)

This paper presents the first two editions of Visual Doom AI Competition, held in 2016 and 2017. The challenge was to create bots that compete in a multi-player deathmatch in a first-person shooter (FPS) game, Doom. The bots had to make their decisions based solely on visual information, i.e., a raw screen buffer. To play well, the bots needed to understand their surroundings, navigate, explore, and handle the opponents at the same time. These aspects, together with the competitive multi-agent aspect of the game, make the competition a unique platform for evaluating the state of the art reinforcement learning algorithms. The paper discusses the rules, solutions, results, and statistics that give insight into the agents' behaviors. Best-performing agents are described in more detail. The results of the competition lead to the conclusion that, although reinforcement learning can produce capable Doom bots, they still are not yet able to successfully compete against humans in this game. The paper also revisits the ViZDoom environment, which is a flexible, easy to use, and efficient 3D platform for research for vision-based reinforcement learning, based on a well-recognized first-person perspective game Doom.