mlsanityData to 7 Oct 2026

A Rubric for Human-like Agents and NeuroAI

arXiv 2212.04401 ↗First posted 8 Dec 2022cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Researchers across cognitive, neuro-, and computer sciences increasingly reference human-like artificial intelligence and neuroAI. However, the scope and use of the terms are often inconsistent. Contributed research ranges widely from mimicking behaviour, to testing machine learning methods as neurally plausible hypotheses at the cellular or functional levels, or solving engineering problems. However, it cannot be assumed nor expected that progress on one of these three goals will automatically translate to progress in others. Here a simple rubric is proposed to clarify the scope of individual contributions, grounded in their commitments to human-like behaviour, neural plausibility, or benchmark/engineering goals. This is clarified using examples of weak and strong neuroAI and human-like agents, and discussing the generative, corroborate, and corrective ways in which the three dimensions interact with one another. The author maintains that future progress in artificial intelligence will need strong interactions across the disciplines, with iterative feedback loops and meticulous validity tests, leading to both known and yet-unknown advances that may span decades to come.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 57 of its 187 references that are in the map. First posted on arXiv 8 Dec 2022.

Builds on

57 of 187 references.

References · 57

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  5. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  6. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  7. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  8. 2015Prioritized Experience Replaycited by 1,070
  9. 2020Mastering Atari with Discrete World Modelscited by 990
  10. 2017To prune, or not to prune: exploring the efficacy of pruning for model compressioncited by 596
  11. 2017Adversarial Patchcited by 514
  12. 2018Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interferencecited by 511
38 more
  1. 2022Using cognitive psychology to understand GPT-3cited by 389
  2. 2015Adversarial Autoencoderscited by 359
  3. 2020Towards Continual Reinforcement Learning: A Review and Perspectivescited by 268
  4. 2018Distributed Prioritized Experience Replaycited by 260
  5. 2021Sustainable AI: Environmental Implications, Challenges and Opportunitiescited by 242
  6. 2019Recurrent Independent Mechanismscited by 219
  7. 2020Revisiting Fundamentals of Experience Replaycited by 171
  8. 2017Neural Episodic Controlcited by 148
  9. 2018Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objectscited by 143
  10. 2019Fast Task Inference with Variational Intrinsic Successor Featurescited by 131
  11. 2017Grounded Language Learning in a Simulated 3D Worldcited by 100
  12. 2017Eigenoption Discovery through the Deep Successor Representationcited by 85
  13. 2020Aligning Superhuman AI with Human Behavior: Chess as a Model Systemcited by 78
  14. 2016Towards an integration of deep learning and neurosciencecited by 77
  15. 2016Towards deep learning with segregated dendritescited by 71
  16. 2017Visual Semantic Planning using Deep Successor Representationscited by 45
  17. 2020Unsupervised deep learning identifies semantic disentanglement in single inferotemporal neuronscited by 33
  18. 2020What can I do here? A Theory of Affordances in Reinforcement Learningcited by 33
  19. 2020Deep Reinforcement Learning and its Neuroscientific Implicationscited by 33
  20. 2021Neural tuning and representational geometrycited by 31
  21. 2020Biologically Inspired Mechanisms for Adversarial Robustnesscited by 29
  22. 2020Deep Reinforcement Learning for Navigation in AAA Video Gamescited by 27
  23. 2018Learning to Prune Filters in Convolutional Neural Networkscited by 25
  24. 2020MEMO: A Deep Network for Flexible Combination of Episodic Memoriescited by 21
  25. 2022Abstraction for Deep Reinforcement Learningcited by 19
  26. 2021Explanatory models in neuroscience: Part 1 -- taking mechanistic abstraction seriouslycited by 18
  27. 2021Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigationcited by 16
  28. 2019A neurally plausible model learns successor representations in partially observable environmentscited by 12
  29. 2019Evolving embodied intelligence from materials to machinescited by 11
  30. 2020The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learningcited by 11
  31. 2020A neural network walks into a lab: towards using deep nets as models for human behaviorcited by 10
  32. 2022Social Network Structure Shapes Innovation: Experience-sharing in RL with SAPIENScited by 10
  33. 2021Interaction-Grounded Learningcited by 9
  34. 2022Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methodscited by 9
  35. 2019Deep Learning for Cognitive Neurosciencecited by 7
  36. 2021Measuring and modeling the motor system with machine learningcited by 7
  37. 2021Explanatory models in neuroscience: Part 2 -- constraint-based intelligibilitycited by 7
  38. 2022Interaction-Grounded Learning with Action-inclusive Feedbackcited by 7

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 3; 2025: 0; 2026: 1.

8 papers.

  1. 2023Evaluating Cognitive Maps and Planning in Large Language Models with CogEvalcited by 77
  2. 2024Is artificial consciousness achievable? Lessons from the human braincited by 11
  3. 2023Predictable Artificial Intelligencecited by 8
  4. 2023Towards Cognitive Bots: Architectural Research Challengescited by 5
  5. 2023Towards Human-Like RL: Taming Non-Naturalistic Behavior in Deep RL via Adaptive Behavioral Costs in 3D Gamescited by 3
  6. 2024Are Transformers Truly Foundational for Robotics?cited by 2
  7. 2024Free Energy Projective Simulation (FEPS): Active inference with interpretabilitycited by 1
  8. 2026Integrative neurocybernetic modeling in the era of large-scale neurosciencecited by 0