AI Learning and Conceptual Transfer in the Game of Hidden Rules

작성자

카테고리:

← 피드로
arXiv cs.AI · Christo Mathew, Wentian Wang, Jacob Feldman, Lazaros K. Gallos, Paul B. Kantor, Vladimir Menkov, Hao Wang · 2026-08-25 AI

[Submitted on 26 Jun 2026]

View PDF HTML (experimental)

Abstract:This report summarizes the work conducted on the Game of Hidden Rules (GOHR), focusing on reinforcement learning agents trained to infer hidden rules from trial-and-error feedback, representation design, rule difficulty analysis, transfer learning, generalization, and pseudo-bot-assisted human learning analysis. The report focuses on the Transformer-based A2C framework, Feature-Centric and Object-Centric representations, experimental findings, and classification of human learning data.

Submission history

From: Christo Mathew [view email]
[v1] Fri, 26 Jun 2026 20:24:43 UTC (4,540 KB)

원문에서 계속 ↗

추출 본문 · 출처: arxiv.org · https://arxiv.org/abs/2608.21372