AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

HogRider: Champion Agent of Microsoft Malmo Collaborative AI Challenge

Yanhai Xiong, Haipeng Chen, Mengchen Zhao, Bo An

AAAI 2018 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Collaborative multi-agent perception

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Separate instead of Weighted action selection (ablation)HogRider · MCAC per stepmean score: 2.527 -> 2.752Improved
use Separate instead of Mixed action selection (ablation)HogRider · MCAC per stepmean score: 2.478 -> 2.752Improved
use Separate instead of Mixed action selection (ablation)HogRider · MCAC per stepvariance/mean: 1.1340 -> 0.9266Improved
use G-Bayes instead of Bayes for type belief update (ablation)HogRider · MCAC per stepoverall detection accuracy: 0.672 -> 0.747Improved
add tanh squashing to G-Bayes belief update (ablation)HogRider · MCAC per stepmean score: 2.505 -> 2.752Improved
add tanh squashing to G-Bayes belief update (ablation)HogRider · MCAC per stepvariance/mean: 0.9062 -> 0.9266Hurt
add tanh squashing to G-Bayes belief update (ablation)HogRider · MCAC per stepoverall detection accuracy: 0.747 -> 0.937Improved
use G-Bayes+tanh instead of traditional Bayes (ablation)HogRider · MCAC per stepmean score: 2.456 -> 2.752Improved
add human reasoning-derived warm start of Q-function (ablation)tabular Q-learning · Pig Chase vs Focused agent, validationmean score: 10.9% improvementImproved
add human reasoning-derived warm start of Q-function (ablation)tabular Q-learning · Pig Chase vs Focused agent, validationvariance/mean: 5.7% decreaseImproved
use active epsilon-greedy instead of Deterministic exploration (ablation)tabular Q-learning · Pig Chase vs Focused agent, validationmean score: 4.1% edgeImproved
use active epsilon-greedy instead of epsilon-greedy exploration (ablation)tabular Q-learning · Pig Chase vs Focused agent, validationmean score: 6.7% edgeImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy