# Investigating Human Priors for Playing Video Games

arXiv: https://arxiv.org/abs/1802.10217 · HTML: https://mlsanity.com/paper/1802.10217/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2018.

## Built on by (most cited first, 30 of 39)

- [Guiding Pretraining in Reinforcement Learning with Large Language Models](https://mlsanity.com/paper/2302.06692/) (2023)
- [Pretraining Representations for Data-Efficient Reinforcement Learning](https://mlsanity.com/paper/2106.04799/) (2021)
- [ActMAD: Activation Matching to Align Distributions for Test-Time-Training](https://mlsanity.com/paper/2211.12870/) (2022)
- [Interesting Object, Curious Agent: Learning Task-Agnostic Exploration](https://mlsanity.com/paper/2111.13119/) (2021)
- [VideoGameBench: Can Vision-Language Models complete popular video games?](https://mlsanity.com/paper/2505.18134/) (2025)
- [MarioNette: Self-Supervised Sprite Learning](https://mlsanity.com/paper/2104.14553/) (2021)
- [OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments](https://mlsanity.com/paper/2306.08649/) (2023)
- [Is an Object-Centric Video Representation Beneficial for Transfer?](https://mlsanity.com/paper/2207.10075/) (2022)
- [Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing](https://mlsanity.com/paper/2107.05545/) (2021)
- [Assessing Adaptive World Models in Machines with Novel Games](https://mlsanity.com/paper/2507.12821/) (2025)
- [Abstraction for Deep Reinforcement Learning](https://mlsanity.com/paper/2202.05839/) (2022)
- [On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning](https://mlsanity.com/paper/2210.10763/) (2022)
- [SILG: The Multi-environment Symbolic Interactive Language Grounding Benchmark](https://mlsanity.com/paper/2110.10661/) (2021)
- [A Comparative Review of Recent Few-Shot Object Detection Algorithms](https://mlsanity.com/paper/2111.00201/) (2021)
- [Perceiving the World: Question-guided Reinforcement Learning for Text-based Games](https://mlsanity.com/paper/2204.09597/) (2022)
- [Reachability-Aware Laplacian Representation in Reinforcement Learning](https://mlsanity.com/paper/2210.13153/) (2022)
- [Intrinsically-Motivated Humans and Agents in Open-World Exploration](https://mlsanity.com/paper/2503.23631/) (2025)
- [Learning to solve complex tasks by growing knowledge culturally across generations](https://mlsanity.com/paper/2107.13377/) (2021)
- [World Models with Hints of Large Language Models for Goal Achieving](https://mlsanity.com/paper/2406.07381/) (2024)
- [Multi-View Feature Representation for Dialogue Generation with Bidirectional Distillation](https://mlsanity.com/paper/2102.10780/) (2021)
- [RePreM: Representation Pre-training with Masked Model for Reinforcement Learning](https://mlsanity.com/paper/2303.01668/) (2023)
- [Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?](https://mlsanity.com/paper/2202.12174/) (2022)
- [Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse](https://mlsanity.com/paper/2605.09965/) (2026)
- [Learning Skills to Navigate without a Master: A Sequential Multi-Policy Reinforcement Learning Algorithm](https://mlsanity.com/paper/2102.00168/) (2021)
- [Towards robust and domain agnostic reinforcement learning competitions](https://mlsanity.com/paper/2106.03748/) (2021)
- [Soft Action Priors: Towards Robust Policy Transfer](https://mlsanity.com/paper/2209.09882/) (2022)
- [Knowledge-Guided Exploration in Deep Reinforcement Learning](https://mlsanity.com/paper/2210.15670/) (2022)
- [The Animal-AI Environment: A Virtual Laboratory For Comparative Cognition and Artificial Intelligence Research](https://mlsanity.com/paper/2312.11414/) (2023)
- [Combining Pre-Trained Models for Enhanced Feature Representation in Reinforcement Learning](https://mlsanity.com/paper/2507.07197/) (2025)
- [Learning Generalizable Behavior via Visual Rewrite Rules](https://mlsanity.com/paper/2112.05218/) (2021)

## 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/