mlsanityData to 7 Oct 2026

Benchmarking End-to-End Behavioural Cloning on Video Games

arXiv 2004.00981 ↗First posted 2 Apr 2020cs.AIcited by 15

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

Abstract (arXiv)

Behavioural cloning, where a computer is taught to perform a task based on demonstrations, has been successfully applied to various video games and robotics tasks, with and without reinforcement learning. This also includes end-to-end approaches, where a computer plays a video game like humans do: by looking at the image displayed on the screen, and sending keystrokes to the game. As a general approach to playing video games, this has many inviting properties: no need for specialized modifications to the game, no lengthy training sessions and the ability to re-use the same tools across different games. However, related work includes game-specific engineering to achieve the results. We take a step towards a general approach and study the general applicability of behavioural cloning on twelve video games, including six modern video games (published after 2010), by using human demonstrations as training data. Our results show that these agents cannot match humans in raw performance but do learn basic dynamics and rules. We also demonstrate how the quality of the data matters, and how recording data from humans is subject to a state-action mismatch, due to human reflexes.

Key facts. Cited by 15 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 24 of its 52 references that are in the map. First posted on arXiv 2 Apr 2020.

Builds on

24 of 52 references.

Closest ancestors · 2

Same direction, newest first

  1. 2019Causal Confusion in Imitation Learning28 May
  2. 2018Imitation Learning with Concurrent Actions in 3D Games14 Mar

Other references · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016Generative Adversarial Imitation Learningcited by 1,576
  4. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  5. 2016End to End Learning for Self-Driving Carscited by 1,000
  6. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 866
  7. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
  8. 2017StarCraft II: A New Challenge for Reinforcement Learningcited by 268
  9. 2018Unity: A General Platform for Intelligent Agentscited by 232
  10. 2019MineRL: A Large-Scale Dataset of Minecraft Demonstrationscited by 210
  11. 2016ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learningcited by 178
  12. 2015Deep Reinforcement Learning in Large Discrete Action Spacescited by 158
10 more
  1. 2019Mastering Complex Control in MOBA Games with Deep Reinforcement Learningcited by 150
  2. 2019Benchmarking Batch Deep Reinforcement Learning Algorithmscited by 108
  3. 2018Learn What Not to Learn: Action Elimination with Deep Reinforcement Learningcited by 77
  4. 2018ViZDoom Competitions: Playing Doom from Pixelscited by 50
  5. 2019Discrete and Continuous Action Representation for Practical RL in Video Gamescited by 34
  6. 2018At Human Speed: Deep Reinforcement Learning with Action Delaycited by 24
  7. 2020Sample Efficient Reinforcement Learning through Learning from Demonstrations in Minecraftcited by 15
  8. 2017The Atari Grand Challenge Datasetcited by 14
  9. 2019Superstition in the Network: Deep Reinforcement Learning Plays Deceptive Gamescited by 4
  10. 2017The Game Imitation: Deep Supervised Convolutional Networks for Quick Video Game AIcited by 3

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 3; 2023: 3; 2024: 4; 2025: 3.

15 papers.

Sort:

By area:

  1. 2022A Generalist Agentcited by 802
  2. 2021Imitation Learning: Progress, Taxonomies and Challengescited by 56
  3. 2021Counter-Strike Deathmatch with Large-Scale Behavioural Cloningcited by 49
  4. 2023DITTO: Offline Imitation Learning with World Modelscited by 20
  5. 2024Zero-shot Imitation Policy via Search in Demonstration Datasetcited by 13
  6. 2023Visual Encoders for Data-Efficient Imitation Learning in Modern Video Gamescited by 6
  7. 2024Will GPT-4 Run DOOM?cited by 6
  8. 2025Adapting a World Model for Trajectory Following in a 3D Gamecited by 5
  9. 2022Configurable Agent With Reward As Input: A Play-Style Continuum Generationcited by 4
  10. 2024Learning to Move Like Professional Counter-Strike Playerscited by 4
  11. 2023Behavioral Cloning via Search in Embedded Demonstration Datasetcited by 3
  12. 2024Online Adaptation for Enhancing Imitation Learning Policiescited by 3
3 more
  1. 2022Improving Behavioural Cloning with Human-Driven Dynamic Dataset Augmentationcited by 1
  2. 2025Learning Representations in Video Game Agents with Supervised Contrastive Imitation Learningcited by 1
  3. 2025VRScout: Towards Real-Time, Autonomous Testing of Virtual Reality Gamescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Behavioural Cloning in VizDoom
  2. 2026Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing
  3. 2019Towards Interactive Training of Non-Player Characters in Video Games
  4. 2024Robust Imitation Learning for Automated Game Testing
  5. 2020Learning to Play by Imitating Humans
  6. 2026NitroGen: An Open Foundation Model for Generalist Gaming Agents
  7. 2019Automated Video Game Testing Using Synthetic and Human-Like Agents
  8. 2022Behavioral Cloning via Search in Video PreTraining Latent Space