mlsanityData to 7 Oct 2026

Investigating Human Priors for Playing Video Games

arXiv 1802.10217 ↗First posted 28 Feb 2018cs.AI cs.LGcited by 39

Not on the map. Why?

Abstract (arXiv)

What makes humans so good at solving seemingly complex video games? Unlike computers, humans bring in a great deal of prior knowledge about the world, enabling efficient decision making. This paper investigates the role of human priors for solving video games. Given a sample game, we conduct a series of ablation studies to quantify the importance of various priors on human performance. We do this by modifying the video game environment to systematically mask different types of visual information that could be used by humans as priors. We find that removal of some prior knowledge causes a drastic degradation in the speed with which human players solve the game, e.g. from 2 minutes to over 20 minutes. Furthermore, our results indicate that general priors, such as the importance of objects and visual consistency, are critical for efficient game-play. Videos and the game manipulations are available at https://rach0012.github.io/humanRL_website/

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 12; 2023: 5; 2024: 2; 2025: 4; 2026: 3.

39 papers.

Sort:

By area:

  1. 2023Guiding Pretraining in Reinforcement Learning with Large Language Modelscited by 185
  2. 2021Pretraining Representations for Data-Efficient Reinforcement Learningcited by 105
  3. 2021Interesting Object, Curious Agent: Learning Task-Agnostic Explorationcited by 38
  4. 2022ActMAD: Activation Matching to Align Distributions for Test-Time-Trainingcited by 38
  5. 2021MarioNette: Self-Supervised Sprite Learningcited by 35
  6. 2023OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environmentscited by 30
  7. 2025VideoGameBench: Can Vision-Language Models complete popular video games?cited by 29
  8. 2022Is an Object-Centric Video Representation Beneficial for Transfer?cited by 24
  9. 2021Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawingcited by 22
  10. 2025Assessing Adaptive World Models in Machines with Novel Gamescited by 20
  11. 2022Abstraction for Deep Reinforcement Learningcited by 19
  12. 2022On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learningcited by 15
27 more
  1. 2021SILG: The Multi-environment Symbolic Interactive Language Grounding Benchmarkcited by 10
  2. 2021A Comparative Review of Recent Few-Shot Object Detection Algorithmscited by 10
  3. 2022Perceiving the World: Question-guided Reinforcement Learning for Text-based Gamescited by 10
  4. 2022Reachability-Aware Laplacian Representation in Reinforcement Learningcited by 10
  5. 2021Learning to solve complex tasks by growing knowledge culturally across generationscited by 6
  6. 2024World Models with Hints of Large Language Models for Goal Achievingcited by 6
  7. 2025Intrinsically-Motivated Humans and Agents in Open-World Explorationcited by 6
  8. 2021Multi-View Feature Representation for Dialogue Generation with Bidirectional Distillationcited by 5
  9. 2023RePreM: Representation Pre-training with Masked Model for Reinforcement Learningcited by 5
  10. 2022Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?cited by 4
  11. 2021Learning Skills to Navigate without a Master: A Sequential Multi-Policy Reinforcement Learning Algorithmcited by 2
  12. 2021Towards robust and domain agnostic reinforcement learning competitionscited by 2
  13. 2022Soft Action Priors: Towards Robust Policy Transfercited by 2
  14. 2022Knowledge-Guided Exploration in Deep Reinforcement Learningcited by 2
  15. 2023The Animal-AI Environment: A Virtual Laboratory For Comparative Cognition and Artificial Intelligence Researchcited by 2
  16. 2025Combining Pre-Trained Models for Enhanced Feature Representation in Reinforcement Learningcited by 2
  17. 2026Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiversecited by 2
  18. 2021Learning Generalizable Behavior via Visual Rewrite Rulescited by 1
  19. 2022Affordance Extraction with an External Knowledge Database for Text-Based Simulated Environmentscited by 1
  20. 2023Strategy Extraction in Single-Agent Gamescited by 1
  21. 2024Learning to Play Video Games with Intuitive Physics Priorscited by 1
  22. 2021Intuitive Physics Guided Exploration for Sample Efficient Sim2real Transfercited by 0
  23. 2021More Efficient Exploration with Symbolic Priors on Action Sequence Equivalencescited by 0
  24. 2022The world seems different in a social context: a neural network analysis of human experimental datacited by 0
  25. 2022Relate to Predict: Towards Task-Independent Knowledge Representations for Reinforcement Learningcited by 0
  26. 2026VLM-Guided Experience Replaycited by 0
  27. 2026Schema: Discovering Unknown Environments via Agentic Program Inductioncited by 0