# HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving

arXiv: https://arxiv.org/abs/2102.11344 · HTML: https://mlsanity.com/paper/2102.11344/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 72 references that are in the map.
- First posted on arXiv 22 Feb 2021.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Learning Invariant Representations for Reinforcement Learning without Reconstruction](https://mlsanity.com/paper/2006.10742/) (2020)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames](https://mlsanity.com/paper/1911.00357/) (2019)
- [Multi-Object Representation Learning with Iterative Variational Inference](https://mlsanity.com/paper/1903.00450/) (2019)
- [Quantifying Generalization in Reinforcement Learning](https://mlsanity.com/paper/1812.02341/) (2018)
- [StarCraft II: A New Challenge for Reinforcement Learning](https://mlsanity.com/paper/1708.04782/) (2017)
- [Emergence of Grounded Compositional Language in Multi-Agent Populations](https://mlsanity.com/paper/1703.04908/) (2017)
- [RAVEN: A Dataset for Relational and Analogical Visual rEasoNing](https://mlsanity.com/paper/1903.02741/) (2019)
- [Attend, Infer, Repeat: Fast Scene Understanding with Generative Models](https://mlsanity.com/paper/1603.08575/) (2016)
- [DeepMDP: Learning Continuous Latent Space Models for Representation Learning](https://mlsanity.com/paper/1906.02736/) (2019)
- [Learning to Navigate in Complex Environments](https://mlsanity.com/paper/1611.03673/) (2016)
- [SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition](https://mlsanity.com/paper/2001.02407/) (2020)
- [Measuring abstract reasoning in neural networks](https://mlsanity.com/paper/1807.04225/) (2018)
- [Value Iteration Networks](https://mlsanity.com/paper/1602.02867/) (2016)
- [Visual Semantic Navigation using Scene Priors](https://mlsanity.com/paper/1810.06543/) (2018)
- [Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input](https://mlsanity.com/paper/1804.03984/) (2018)
- [An investigation of model-free planning](https://mlsanity.com/paper/1901.03559/) (2019)
- [Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense](https://mlsanity.com/paper/2004.09044/) (2020)
- [Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics](https://mlsanity.com/paper/1706.04317/) (2017)
- [Unsupervised Predictive Memory in a Goal-Directed Agent](https://mlsanity.com/paper/1803.10760/) (2018)

## Built on by (most cited first, 15 of 15)

- [A Survey of Zero-shot Generalisation in Deep Reinforcement Learning](https://mlsanity.com/paper/2111.09794/) (2021)
- [Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution](https://mlsanity.com/paper/2103.14230/) (2021)
- [Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions](https://mlsanity.com/paper/2205.13803/) (2022)
- [ACRE: Abstract Causal REasoning Beyond Covariation](https://mlsanity.com/paper/2103.14232/) (2021)
- [SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation](https://mlsanity.com/paper/2310.16838/) (2023)
- [Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World](https://mlsanity.com/paper/2310.10207/) (2023)
- [MEWL: Few-shot multimodal word learning with referential uncertainty](https://mlsanity.com/paper/2306.00503/) (2023)
- [RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning](https://mlsanity.com/paper/2204.11167/) (2022)
- [I-PHYRE: Interactive Physical Reasoning](https://mlsanity.com/paper/2312.03009/) (2023)
- [Neural-Symbolic Recursive Machine for Systematic Generalization](https://mlsanity.com/paper/2210.01603/) (2022)
- [Interactive Visual Reasoning under Uncertainty](https://mlsanity.com/paper/2206.09203/) (2022)
- [Active Reasoning in an Open-World Environment](https://mlsanity.com/paper/2311.02018/) (2023)
- [A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics](https://mlsanity.com/paper/2103.01403/) (2021)
- [On the Complexity of Bayesian Generalization](https://mlsanity.com/paper/2211.11033/) (2022)
- [AIGenC: An AI generalisation model via creativity](https://mlsanity.com/paper/2205.09738/) (2022)

## Abstract (arXiv)

Humans learn compositional and causal abstraction, ie, knowledge, in response to the structure of naturalistic tasks. When presented with a problem-solving task involving some objects, toddlers would first interact with these objects to reckon what they are and what can be done with them. Leveraging these concepts, they could understand the internal structure of this task, without seeing all of the problem instances. Remarkably, they further build cognitively executable strategies to rapidly solve novel problems. To empower a learning agent with similar capability, we argue there shall be three levels of generalization in how an agent represents its knowledge: perceptual, conceptual, and algorithmic. In this paper, we devise the very first systematic benchmark that offers joint evaluation covering all three levels. This benchmark is centered around a novel task domain, HALMA, for visual concept development and rapid problem-solving. Uniquely, HALMA has a minimum yet complete concept space, upon which we introduce a novel paradigm to rigorously diagnose and dissect learning agents' capability in understanding and generalizing complex and structural concepts. We conduct extensive experiments on reinforcement learning agents with various inductive biases and carefully report their proficiency and weakness.