mlsanityData to 14 Oct 2026

Towards Understanding How Machines Can Learn Causal Overhypotheses

arXiv 2206.08353 ↗First posted 16 Jun 2022cs.LG stat.MLcited by 14

Not on the map. Why?

Abstract (arXiv)

Recent work in machine learning and cognitive science has suggested that understanding causal information is essential to the development of intelligence. The extensive literature in cognitive science using the ``blicket detector'' environment shows that children are adept at many kinds of causal inference and learning. We propose to adapt that environment for machine learning agents. One of the key challenges for current machine learning algorithms is modeling and understanding causal overhypotheses: transferable abstract hypotheses about sets of causal relationships. In contrast, even young children spontaneously learn and use causal overhypotheses. In this work, we present a new benchmark -- a flexible environment which allows for the evaluation of existing techniques under variable causal overhypotheses -- and demonstrate that many existing state-of-the-art methods have trouble generalizing in this environment. The code and resources for this benchmark are available at https://github.com/CannyLab/casual_overhypotheses.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 37 of its 52 references that are in the map. First posted on arXiv 16 Jun 2022.

Builds on

37 of 52 references.

References · 37

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  4. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  5. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  6. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  7. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  8. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  9. 2018Exploration by Random Network Distillationcited by 993
  10. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  11. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 689
  12. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 639
25 more
  1. 2022Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Modelcited by 559
  2. 2016Deep Exploration via Bootstrapped DQNcited by 527
  3. 2018Quantifying Generalization in Reinforcement Learningcited by 352
  4. 2016#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learningcited by 309
  5. 2017Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agentscited by 269
  6. 2019Self-Supervised Exploration via Disagreementcited by 265
  7. 2017Count-Based Exploration with Neural Density Modelscited by 257
  8. 2018BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learningcited by 244
  9. 2019Recurrent Independent Mechanismscited by 219
  10. 2021Towards Causal Representation Learningcited by 209
  11. 2019A Meta-Transfer Objective for Learning to Disentangle Causal Mechanismscited by 158
  12. 2019PHYRE: A New Benchmark for Physical Reasoningcited by 137
  13. 2018Count-Based Exploration with the Successor Representationcited by 112
  14. 2020CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learningcited by 109
  15. 2021Neural Production Systems: Learning Rule-Governed Visual Dynamicscited by 75
  16. 2021A Survey of Exploration Methods in Reinforcement Learningcited by 73
  17. 2019Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoningcited by 61
  18. 2018Gotta Learn Fast: A New Benchmark for Generalization in RLcited by 59
  19. 2020Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learningcited by 53
  20. 2021Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learningcited by 53
  21. 2017Count-Based Exploration in Feature Space for Reinforcement Learningcited by 49
  22. 2021ACRE: Abstract Causal REasoning Beyond Covariationcited by 30
  23. 2021CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoningcited by 23
  24. 2022Learning Causal Overhypotheses through Exploration in Children and Computational Modelscited by 7
  25. 2020Exploring Exploration: Comparing Children with RL Agents in Unified Environmentscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 3; 2025: 2; 2026: 3.

14 papers.

Sort:

By area:

  1. 2022Using cognitive psychology to understand GPT-3cited by 398
  2. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 353
  3. 2024Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Surveycited by 83
  4. 2023MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Taskscited by 44
  5. 2023Visual cognition in multimodal large language modelscited by 38
  6. 2024AI for social science and social science of AI: A Surveycited by 29
  7. 2023Passive learning of active causal strategies in agents and language modelscited by 21
  8. 2023Imitation versus Innovation: What children can do that large language and language-and-vision models cannot (yet)?cited by 13
  9. 2025Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think Like Scientists?cited by 7
  10. 2024CogLM: Tracking Cognitive Development of Large Language Modelscited by 4
  11. 2025Leveraging Large Language Models for Automated Causal Loop Diagram Generation: Enhancing System Dynamics Modeling through Curated Prompting Techniquescited by 1
  12. 2026Separable Pathways for Causal Reasoning: How Architectural Scaffolding Enables Hypothesis-Space Restructuring in LLM Agentscited by 0
2 more
  1. 2026DTO: a Differentiable Training Objective for Effective Counterfactual Story Rewritingcited by 0
  2. 2026ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universecited by 0