AI Learning and Conceptual Transfer in the Game of Hidden Rules
On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. Builds on 3 of its 9 references that are in the map. First posted on arXiv 26 Jun 2026.
Builds on
3 of 9 references.
Closest ancestors · 1
Same direction, newest first
- 2025Toward a Metrology for Artificial Intelligence: Hidden-Rule Environments and Reinforcement Learning7 Sep
Other references · 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Interpretable GOHR Agents via Sparse Autoencoders
- 2026Towards the Automatic Synthesis of Interpretable Chess Tactics
- 2026Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition
- 2024Baba Is AI: Break the Rules to Beat the Benchmark
- 2026Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction
- 2025InnateCoder: Learning Programmatic Options with Foundation Models
- 2022Understanding Game-Playing Agents with Natural Language Annotations
- 2022Multi-Game Decision Transformers