# Language and Culture Internalisation for Human-Like Autotelic AI arXiv: https://arxiv.org/abs/2206.01134 ยท HTML: https://mlsanity.com/paper/2206.01134/ ## Key facts - Cited by 14 papers in the map (data through 14 Oct 2026). - Builds on 46 of its 126 references that are in the map. - First posted on arXiv 2 Jun 2022. ## Builds on (most cited first, 30 of 46) - [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018) - [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021) - [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020) - [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022) - [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022) - [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022) - [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021) - [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022) - [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020) - [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017) - [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022) - [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021) - [Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://mlsanity.com/paper/2204.00598/) (2022) - [Embodied Question Answering](https://mlsanity.com/paper/1711.11543/) (2017) - [Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning](https://mlsanity.com/paper/2205.09712/) (2022) - [TextWorld: A Learning Environment for Text-based Games](https://mlsanity.com/paper/1806.11532/) (2018) - [Towards Understanding and Mitigating Social Biases in Language Models](https://mlsanity.com/paper/2106.13219/) (2021) - [Symbolic Knowledge Distillation: from General Language Models to Commonsense Models](https://mlsanity.com/paper/2110.07178/) (2021) - [Visual Reinforcement Learning with Imagined Goals](https://mlsanity.com/paper/1807.04742/) (2018) - [Experience Grounds Language](https://mlsanity.com/paper/2004.10151/) (2020) - [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022) - [Language Conditioned Imitation Learning over Unstructured Data](https://mlsanity.com/paper/2005.07648/) (2020) - [Open-Ended Learning Leads to Generally Capable Agents](https://mlsanity.com/paper/2107.12808/) (2021) - [Probing Pre-Trained Language Models for Cross-Cultural Differences in Values](https://mlsanity.com/paper/2203.13722/) (2022) - [Language as an Abstraction for Hierarchical Deep Reinforcement Learning](https://mlsanity.com/paper/1906.07343/) (2019) - [Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview](https://mlsanity.com/paper/1912.11078/) (2019) - [Grounded Language Learning in a Simulated 3D World](https://mlsanity.com/paper/1706.06551/) (2017) - [Skill Induction and Planning with Latent Language](https://mlsanity.com/paper/2110.01517/) (2021) - [Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey](https://mlsanity.com/paper/2012.09830/) (2020) - [Learning to Understand Goal Specifications by Modelling Reward](https://mlsanity.com/paper/1806.01946/) (2018) ## Built on by (most cited first, 14 of 14) - [Scaling Instructable Agents Across Many Simulated Worlds](https://mlsanity.com/paper/2404.10179/) (2024) - [OMNI: Open-endedness via Models of human Notions of Interestingness](https://mlsanity.com/paper/2306.01711/) (2023) - [Augmenting Autotelic Agents with Large Language Models](https://mlsanity.com/paper/2305.12487/) (2023) - [A social path to human-like artificial intelligence](https://mlsanity.com/paper/2405.15815/) (2024) - [Is artificial consciousness achievable? Lessons from the human brain](https://mlsanity.com/paper/2405.04540/) (2024) - [MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces](https://mlsanity.com/paper/2502.07709/) (2025) - [Policy Learning with a Language Bottleneck](https://mlsanity.com/paper/2405.04118/) (2024) - [Intrinsic Motivation in Model-based Reinforcement Learning: A Brief Review](https://mlsanity.com/paper/2301.10067/) (2023) - [Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination](https://mlsanity.com/paper/2602.20517/) (2026) - [Language and Experience: A Computational Model of Social Learning in Complex Tasks](https://mlsanity.com/paper/2509.00074/) (2025) - [A Song of Ice and Fire: Analyzing Textual Autotelic Agents in ScienceWorld](https://mlsanity.com/paper/2302.05244/) (2023) - [Leveraging Retrieval-Augmented Generation for Culturally Inclusive Hakka Chatbots: Design Insights and User Perceptions](https://mlsanity.com/paper/2410.15572/) (2024) - [HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents](https://mlsanity.com/paper/2508.14751/) (2025) - [Position: Introspective Experience from Conversational Environments as a Path to Better Learning](https://mlsanity.com/paper/2602.14910/) (2026) ## 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.