mlsanityData to 7 Oct 2026

Language and Culture Internalisation for Human-Like Autotelic AI

arXiv 2206.01134 ↗First posted 2 Jun 2022cs.AI cs.CL cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Building autonomous agents able to grow open-ended repertoires of skills across their lives is a fundamental goal of artificial intelligence (AI). A promising developmental approach recommends the design of intrinsically motivated agents that learn new skills by generating and pursuing their own goals - autotelic agents. But despite recent progress, existing algorithms still show serious limitations in terms of goal diversity, exploration, generalisation or skill composition. This perspective calls for the immersion of autotelic agents into rich socio-cultural worlds, an immensely important attribute of our environment that shapes human cognition but is mostly omitted in modern AI. Inspired by the seminal work of Vygotsky, we propose Vygotskian autotelic agents - agents able to internalise their interactions with others and turn them into cognitive tools. We focus on language and show how its structure and informational content may support the development of new cognitive functions in artificial agents as it does in humans. We justify the approach by uncovering several examples of new artificial cognitive functions emerging from interactions between language and embodiment in recent works at the intersection of deep reinforcement learning and natural language processing. Looking forward, we highlight future opportunities and challenges for Vygotskian Autotelic AI research, including the use of language models as cultural models supporting artificial cognitive development.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 46 of its 126 references that are in the map. First posted on arXiv 2 Jun 2022.

Builds on

46 of 126 references.

References · 46

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  6. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  7. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  8. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  9. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  10. 2017Hindsight Experience Replaycited by 1,096
  11. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  12. 2021Ethical and social risks of harm from Language Modelscited by 957
34 more
  1. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  2. 2017Embodied Question Answeringcited by 335
  3. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
  4. 2018TextWorld: A Learning Environment for Text-based Gamescited by 304
  5. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 294
  6. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  7. 2018Visual Reinforcement Learning with Imagined Goalscited by 248
  8. 2020Experience Grounds Languagecited by 241
  9. 2022Challenges and Strategies in Cross-Cultural NLPcited by 216
  10. 2020Language Conditioned Imitation Learning over Unstructured Datacited by 208
  11. 2021Open-Ended Learning Leads to Generally Capable Agentscited by 177
  12. 2022Probing Pre-Trained Language Models for Cross-Cultural Differences in Valuescited by 147
  13. 2019Language as an Abstraction for Hierarchical Deep Reinforcement Learningcited by 138
  14. 2019Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overviewcited by 137
  15. 2017Grounded Language Learning in a Simulated 3D Worldcited by 100
  16. 2021Skill Induction and Planning with Latent Languagecited by 99
  17. 2020Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Surveycited by 83
  18. 2018Learning to Understand Goal Specifications by Modelling Rewardcited by 80
  19. 2018CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learningcited by 78
  20. 2020Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Explorationcited by 68
  21. 2020Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Textcited by 59
  22. 2022Semantic Exploration from Language Abstractions and Pretrained Representationscited by 51
  23. 2022Improving Intrinsic Exploration with Language Abstractionscited by 49
  24. 2021Leveraging Language to Learn Program Abstractions and Search Heuristicscited by 44
  25. 2021ELLA: Exploration through Learned Language Abstractioncited by 42
  26. 2021Tell me why! Explanations support learning relational and causal structurecited by 36
  27. 2020Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learningcited by 32
  28. 2021Interactive Learning from Activity Descriptioncited by 26
  29. 2021Symbolic Behaviour in Artificial Intelligencecited by 24
  30. 2018Measuring and Characterizing Generalization in Deep Reinforcement Learningcited by 20
  31. 2020Inverse Reinforcement Learning with Natural Language Goalscited by 20
  32. 2019Interactive Language Learning by Question Answeringcited by 19
  33. 2022Abstraction for Deep Reinforcement Learningcited by 19
  34. 2021Grounding Spatio-Temporal Language with Transformerscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 5; 2025: 3; 2026: 2.

14 papers.

Sort:

By area:

  1. 2024Scaling Instructable Agents Across Many Simulated Worldscited by 67
  2. 2023OMNI: Open-endedness via Models of human Notions of Interestingnesscited by 66
  3. 2023Augmenting Autotelic Agents with Large Language Modelscited by 29
  4. 2024A social path to human-like artificial intelligencecited by 20
  5. 2024Is artificial consciousness achievable? Lessons from the human braincited by 11
  6. 2025MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spacescited by 7
  7. 2024Policy Learning with a Language Bottleneckcited by 4
  8. 2023Intrinsic Motivation in Model-based Reinforcement Learning: A Brief Reviewcited by 3
  9. 2026Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordinationcited by 2
  10. 2025Language and Experience: A Computational Model of Social Learning in Complex Taskscited by 1
  11. 2023A Song of Ice and Fire: Analyzing Textual Autotelic Agents in ScienceWorldcited by 0
  12. 2024Leveraging Retrieval-Augmented Generation for Culturally Inclusive Hakka Chatbots: Design Insights and User Perceptionscited by 0
2 more
  1. 2025HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agentscited by 0
  2. 2026Position: Introspective Experience from Conversational Environments as a Path to Better Learningcited by 0