mlsanityData to 7 Oct 2026

Counter-Strike Deathmatch with Large-Scale Behavioural Cloning

arXiv 2104.04258 ↗First posted 9 Apr 2021cs.AI cs.LG stat.MLcited by 49

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

This paper describes an AI agent that plays the popular first-person-shooter (FPS) video game `Counter-Strike; Global Offensive' (CSGO) from pixel input. The agent, a deep neural network, matches the performance of the medium difficulty built-in AI on the deathmatch game mode, whilst adopting a humanlike play style. Unlike much prior work in games, no API is available for CSGO, so algorithms must train and run in real-time. This limits the quantity of on-policy data that can be generated, precluding many reinforcement learning algorithms. Our solution uses behavioural cloning - training on a large noisy dataset scraped from human play on online servers (4 million frames, comparable in size to ImageNet), and a smaller dataset of high-quality expert demonstrations. This scale is an order of magnitude larger than prior work on imitation learning in FPS games.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 15 of its 47 references that are in the map. First posted on arXiv 9 Apr 2021.

Builds on

15 of 47 references.

Closest ancestors · 3

Same direction, newest first

  1. 2020Benchmarking End-to-End Behavioural Cloning on Video Games2 Apr
  2. 2019Causal Confusion in Imitation Learning28 May
  3. 2018Imitation Learning with Concurrent Actions in 3D Games14 Mar

Other references · 12

  1. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  2. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  3. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
  4. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  5. 2018Human-level performance in first-person multiplayer games with population-based deep reinforcement learningcited by 260
  6. 2019MineRL: A Large-Scale Dataset of Minecraft Demonstrationscited by 210
  7. 2016ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learningcited by 178
  8. 2016Playing FPS Games with Deep Reinforcement Learningcited by 95
  9. 2016DeepMind Labcited by 74
  10. 2018ViZDoom Competitions: Playing Doom from Pixelscited by 50
  11. 2020SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft IIcited by 22
  12. 2017The Game Imitation: Deep Supervised Convolutional Networks for Quick Video Game AIcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 5; 2024: 11; 2025: 21; 2026: 7.

49 papers.

Sort:

By area:

  1. 2024Diffusion for World Modeling: Visual Details Matter in Ataricited by 285
  2. 2023Imitating Human Behaviour with Diffusion Modelscited by 260
  3. 2024Scaling Instructable Agents Across Many Simulated Worldscited by 67
  4. 2025Vid2World: Crafting Video Diffusion Models to Interactive World Modelscited by 67
  5. 2025SIMA 2: A Generalist Embodied Agent for Virtual Worldscited by 26
  6. 2023TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Playcited by 18
  7. 2025StateSpaceDiffuser: Bringing Long Context to Diffusion World Modelscited by 16
  8. 2022Model-based Trajectory Stitching for Improved Offline Reinforcement Learningcited by 15
  9. 2025Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulationcited by 10
  10. 2023Denoising Heat-inspired Diffusion with Insulators for Collision Free Motion Planningcited by 8
  11. 2022Model-based trajectory stitching for improved behavioural cloning and its applicationscited by 7
  12. 2023Visual Encoders for Data-Efficient Imitation Learning in Modern Video Gamescited by 6
37 more
  1. 2024Predicting Long-Term Human Behaviors in Discrete Representations via Physics-Guided Diffusioncited by 6
  2. 2025ROCKET-2: Steering Visuomotor Policy via Cross-View Goal Alignmentcited by 6
  3. 2024BehAVE: Behaviour Alignment of Video Game Encodingscited by 5
  4. 2024Training Interactive Agent in Large FPS Game Map with Rule-enhanced Reinforcement Learningcited by 5
  5. 2025Adapting a World Model for Trajectory Following in a 3D Gamecited by 5
  6. 2022Self-Imitation Learning from Demonstrationscited by 4
  7. 2023Improving Generalization in Game Agents with Data Augmentation in Imitation Learningcited by 4
  8. 2024Learning to Move Like Professional Counter-Strike Playerscited by 4
  9. 2024Bellman Diffusion: Generative Modeling as Learning a Linear Operator in the Distribution Spacecited by 4
  10. 2025Toward Stable World Models: Measuring and Addressing World Instability in Generative Environmentscited by 4
  11. 2026Nano World Models: A Minimalist Implementation of Future Video Predictioncited by 4
  12. 2024Reinforcement Learning for High-Level Strategic Control in Tower Defense Gamescited by 3
  13. 2025Real-Time Diffusion Policies for Games: Enhancing Consistency Policies with Q-Ensemblescited by 3
  14. 2025Pixels to Play: A Foundation Model for 3D Gameplaycited by 3
  15. 2025D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AIcited by 3
  16. 2025TV2TV: A Unified Framework for Interleaved Language and Video Generationcited by 3
  17. 2026When Does Predictive Inverse Dynamics Outperform Behavior Cloning?cited by 3
  18. 2024Behavioural Cloning in VizDoomcited by 2
  19. 2024Affectively Framework: Towards Human-like Affect-Based Agentscited by 2
  20. 2025Generative Modeling of Individual Behavior at Scalecited by 2
  21. 2025pix2pockets: Shot Suggestions in 8-Ball Pool from a Single Image in the Wildcited by 2
  22. 2026Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiversecited by 2
  23. 2022WILD-SCAV: Benchmarking FPS Gaming AI on Unity3D-based Environmentscited by 1
  24. 2024Human-like Bots for Tactical Shooters Using Compute-Efficient Sensorscited by 1
  25. 2025Path Generation and Evaluation in Video Games: A Nonparametric Statistical Approachcited by 1
  26. 2025Learning Dark Souls Combat Through Pixel Input With Neuroevolutioncited by 1
  27. 2025Playing Atari Space Invaders with Sparse Cosine Optimized Policy Evolutioncited by 1
  28. 2025Learning to play: A Multimodal Agent for 3D Game-Playcited by 1
  29. 2022Human-Like Navigation Behavior: A Statistical Evaluation Frameworkcited by 0
  30. 2025Eval-PPO: Building an Efficient Threat Evaluator Using Proximal Policy Optimizationcited by 0
  31. 2025Play Style Identification Using Low-Level Representations of Play Traces in MicroRTScited by 0
  32. 2025Combining Reinforcement Learning and Behavior Trees for NPCs in Video Games with AMD Scholacited by 0
  33. 2025VRScout: Towards Real-Time, Autonomous Testing of Virtual Reality Gamescited by 0
  34. 2026Augmenting Game AI with Deep Reinforcement Learningcited by 0
  35. 2026Augmentations for Robust and Efficient Imitation Learning in Streamed Video Gamescited by 0
  36. 2026Cortex: Compact Behavior Cloning for Quake with Frozen Visual Featurescited by 0
  37. 2026DSLE: A Learning Environment for Dark Souls Boss Encounterscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Reinforcement Learning Agent for a 2D Shooter Game
  2. 2019Towards Interactive Training of Non-Player Characters in Video Games
  3. 2023Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Competitive Games
  4. 2025Human-Level Competitive Pok'emon via Scalable Offline Reinforcement Learning with Transformers
  5. 2026NitroGen: An Open Foundation Model for Generalist Gaming Agents
  6. 2024Robust Imitation Learning for Automated Game Testing
  7. 2026Account Consistency from Gameplay Traces: Same-Player Verification in Counter-Strike 2
  8. 2020TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game