Toward a Metrology for Artificial Intelligence: Hidden-Rule Environments and Reinforcement Learning
On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization
Abstract (arXiv)
We investigate reinforcement learning in the Game Of Hidden Rules (GOHR) environment, a complex puzzle in which an agent must infer and execute hidden rules to clear a 6×6 board by placing game pieces into buckets. We explore two state representation strategies, namely Feature-Centric (FC) and Object-Centric (OC), and employ a Transformer-based Advantage Actor-Critic (A2C) algorithm for training. The agent has access only to partial observations and must simultaneously infer the governing rule and learn the optimal policy through experience. We evaluate our models across multiple rule-based and trial-list-based experimental setups, analyzing transfer effects and the impact of representation on learning efficiency.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. Builds on 8 of its 28 references that are in the map. First posted on arXiv 7 Sep 2025.
Builds on
8 of 28 references.
References · 8
- 2024The Llama 3 Herd of Modelscited by 14,715
- 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
- 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
- 2023The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domaincited by 101
- 2023Large Language Models Are Not Strong Abstract Reasonerscited by 53
- 2022The Game of Hidden Rules: A New Kind of Benchmark Challenge for Machine Learningcited by 4
- 2019Can We Distinguish Machine Learning from Human Learning?cited by 3
- 2023Comparing Reinforcement Learning and Human Learning using the Game of Hidden Rulescited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2026Interpretable GOHR Agents via Sparse Autoencoders
- 2026Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition
- 2026Witness: Discovery, Deciphering, and Epiphany in Interactive Puzzle Environments
- 2021Learning Generalizable Behavior via Visual Rewrite Rules
- 2023Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery
- 2026Player-1: Learning to Play from Synthetic Experience
- 2025Policy-Conditioned Policies for Multi-Agent Task Solving
- 2025Learning Game-Playing Agents with Generative Code Optimization