Investigating Human Priors for Playing Video Games

Abstract

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/

arXiv commentICML 2018

References in corpus (4)

• Unifying Count-Based Exploration and Intrinsic Motivation
• Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics
• Value Prediction Network
• Grounding Language for Transfer in Deep Reinforcement Learning

Cited by in corpus (26)

• Learning to Paint With Model-based Deep Reinforcement Learning
• Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning
• Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement
• On Inductive Biases in Deep Reinforcement Learning
• A Survey on Interactive Reinforcement Learning: Design Principles and Open Challenges
• A Comparative Review of Recent Few-Shot Object Detection Algorithms
• Task-Agnostic Dynamics Priors for Deep Reinforcement Learning
• The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning
• Retrospective Analysis of the 2019 MineRL Competition on Sample Efficient Reinforcement Learning
• Injecting Prior Knowledge for Transfer Learning into Reinforcement Learning Algorithms using Logic Tensor Networks
• Exploring Exploration: Comparing Children with RL Agents in Unified Environments
• Toybox: A Suite of Environments for Experimental Evaluation of Deep Reinforcement Learning
• Meta-Learning of Structured Task Distributions in Humans and Machines
• Guaranteeing Reproducibility in Deep Learning Competitions
• Learning to Play General Video-Games via an Object Embedding Network
• The relationship between Biological and Artificial Intelligence
• ALPaCA vs. GP-based Prior Learning: A Comparison between two Bayesian Meta-Learning Algorithms
• Generalization to Novel Objects using Prior Relational Knowledge
• SILG: The Multi-environment Symbolic Interactive Language Grounding Benchmark
• Towards robust and domain agnostic reinforcement learning competitions
• The world seems different in a social context: a neural network analysis of human experimental data
• Learning-Based Video Game Development in MLP@UoM: An Overview
• Zero-shot Policy Learning with Spatial Temporal RewardDecomposition on Contingency-aware Observation
• Compositional Networks Enable Systematic Generalization for Grounded Language Understanding
• MarioNette: Self-Supervised Sprite Learning
• Sim-to-Real Transfer of Robot Learning with Variable Length Inputs