mlsanityData to 14 Oct 2026

Learning Robust Real-Time Cultural Transmission without Human Data

arXiv 2203.00715 ↗First posted 1 Mar 2022cs.LG cs.AI cs.MAcited by 9

Not on the map. Why?

Abstract (arXiv)

Cultural transmission is the domain-general social skill that allows agents to acquire and use information from each other in real-time with high fidelity and recall. In humans, it is the inheritance process that powers cumulative cultural evolution, expanding our skills, tools and knowledge across generations. We provide a method for generating zero-shot, high recall cultural transmission in artificially intelligent agents. Our agents succeed at real-time cultural transmission from humans in novel contexts without using any pre-collected human data. We identify a surprisingly simple set of ingredients sufficient for generating cultural transmission and develop an evaluation methodology for rigorously assessing it. This paves the way for cultural evolution as an algorithm for developing artificial general intelligence.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 70 of its 150 references that are in the map. First posted on arXiv 1 Mar 2022.

Builds on

70 of 150 references.

References · 70

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  4. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  5. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  6. 2016Understanding intermediate layers using linear classifier probescited by 1,353
  7. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  8. 2018Exploration by Random Network Distillationcited by 993
  9. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 752
  10. 2019Solving Rubik's Cube with a Robot Handcited by 734
  11. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 672
  12. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 639
38 more
  1. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 604
  2. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 503
  3. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 483
  4. 2016Reinforcement Learning with Unsupervised Auxiliary Taskscited by 404
  5. 2016Learning to reinforcement learncited by 377
  6. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 349
  7. 2018Maximum a Posteriori Policy Optimisationcited by 328
  8. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 313
  9. 2020Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Designcited by 275
  10. 2017Noisy Networks for Explorationcited by 266
  11. 2016Safe and Efficient Off-Policy Reinforcement Learningcited by 264
  12. 2018Human-level performance in first-person multiplayer games with population-based deep reinforcement learningcited by 264
  13. 2018Unity: A General Platform for Intelligent Agentscited by 236
  14. 2018Machine Theory of Mindcited by 226
  15. 2016Learning to Navigate in Complex Environmentscited by 198
  16. 2020"Other-Play" for Zero-Shot Coordinationcited by 198
  17. 2019The Hanabi Challenge: A New Frontier for AI Researchcited by 197
  18. 2020The Next Decade in AI: Four Steps Towards Robust Artificial Intelligencecited by 195
  19. 2019Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutionscited by 192
  20. 2021Open-Ended Learning Leads to Generally Capable Agentscited by 182
  21. 2018A Study on Overfitting in Deep Reinforcement Learningcited by 174
  22. 2017Parameter Space Noise for Explorationcited by 161
  23. 2017Deep Exploration via Randomized Value Functionscited by 156
  24. 2019Unsupervised State Representation Learning in Ataricited by 144
  25. 2021Collaborating with Humans without Human Datacited by 142
  26. 2018Meta-Reinforcement Learning of Structured Exploration Strategiescited by 130
  27. 2020Effective Diversity in Population Based Reinforcement Learningcited by 119
  28. 2021Replay-Guided Adversarial Environment Designcited by 111
  29. 2018Learning to Navigate in Cities Without a Mapcited by 104
  30. 2018Imitating Latent Policies from Observationcited by 101
  31. 2019Recent Advances in Imitation Learning from Observationcited by 93
  32. 2020Offline Meta-Reinforcement Learning with Advantage Weightingcited by 93
  33. 2019AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligencecited by 86
  34. 2018Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generationcited by 81
  35. 2016Loss is its own Reward: Self-Supervision for Reinforcement Learningcited by 72
  36. 2019Meta-learning of Sequential Strategiescited by 70
  37. 2018Diversity-Driven Exploration Strategy for Deep Reinforcement Learningcited by 65
  38. 2019Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Researchcited by 61

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 2; 2024: 2; 2025: 1.

9 papers.

  1. 2023Human-Timescale Adaptation in an Open-Ended Task Spacecited by 138
  2. 2022Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goalscited by 126
  3. 2022Emergent Communication: Generalization and Overfitting in Lewis Gamescited by 28
  4. 2023The SocialAI School: Insights from Developmental Psychology Towards Artificial Socio-Cultural Agentscited by 24
  5. 2025Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worldscited by 4
  6. 2022Adaptive patch foraging in deep reinforcement learning agentscited by 3
  7. 2022Developing, Evaluating and Scaling Learning Agents in Multi-Agent Environmentscited by 2
  8. 2024Emergent Dominance Hierarchies in Reinforcement Learning Agentscited by 1
  9. 2024Social Interpretable Reinforcement Learningcited by 0