Research graph
References from Self-generated goals in the age of foundation models: artificial autotelic agents and their implications for cognitive science. Local targets link to admitted publications; unresolved targets remain external evidence.
What Is Artificial Intelligence?
2007 · External reference
Unresolved reference
2014 · External reference
Inpraise of folly: flexible goals and human cognition
10.1016/j.tics.2024.03.006 · 2024 · External reference
A goal-centric outlook on learning
10.1016/j.tics.2023.08.011 · 2023 · External reference
The evolution of agency
2023 · External reference
Autotelic agents with intrinsically motivated goal-conditioned reinforcement learning: a short survey
10.1613/jair.1.13554 · 2022 · External reference
Unresolved reference
External reference
Unresolved reference
2018 · External reference
What is intrinsic motivation? A typology of computational approaches
10.3389/neuro.12.006.2007 · 2007 · External reference
Intrinsically motivated reinforcement learning: an evolutionary perspective
10.1109/tamd.2010.2051031 · 2010 · External reference
Play, curiosity, and cognition
10.1146/annurev-devpsych-070120-014806 · 2020 · External reference
Spontaneous thought as play: the value of fictional goals in the default mode network
2025 · External reference
The Evolution of Human Goals
10.1111/tops.70078 · 2026 · External reference
Unresolved reference
2013 · External reference
What do we learn about development from baby robots?
10.1002/wcs.1395 · 2017 · External reference
10.7551/mitpress/3115.003.0030
10.7551/mitpress/3115.003.0030 · External reference
Unresolved reference
External reference
Goals as reward-producing programs
10.1038/s42256-025-00981-4 · 2025 · External reference
Guiding pretraining in reinforcement learning with large language models
2023 · External reference
Unresolved reference
External reference
Voyager: an open-ended embodied agent with large language models
2024 · External reference
Universal value function approximators
2015 · External reference
Unresolved reference
1993 · External reference
Hindsight experience replay
2017 · External reference
Midbrain dopamine neurons signal preference for advance information about upcoming rewards
10.1016/j.neuron.2009.06.009 · 2009 · External reference
Valuation of knowledge and ignorance in mesolimbic reward circuitry
10.1073/pnas.1800547115 · 2018 · External reference
Intrinsic motivation for choice varies with individual risk attitudes and the controllability of the environment
2023 · External reference
Skew-fit: state-covering self-supervised reinforcement learning
2020 · External reference
Automatic goal generation for reinforcement learning agents
2018 · External reference
Unresolved reference
External reference
Curious: intrinsically motivated modular multi-goal reinforcement learning
2019 · External reference
Intrinsically motivated goal exploration processes with automatic curriculum learning
2022 · External reference
A unified model of speech and tool use early development
2017 · External reference
GRAIL: a goal-discovering robotic architecture for intrinsically-motivated learning
10.1109/tcds.2016.2538961 · 2016 · External reference
Unresolved reference
External reference
Unresolved reference
2018 · External reference
Unresolved reference
2020 · External reference
Human-timescale adaptation in an open-ended task space
2023 · External reference
Unresolved reference
External reference
Unresolved reference
External reference
ACES: generating diverse programming puzzles with autotelic language models and semantic descriptors
10.52202/079017-2160 · 2024 · External reference
OMNI-EPIC: open-endedness via models of human notions of interestingness with environments programmed in code
2025 · External reference
Language and culture internalization for human-like autotelic ai
10.1038/s42256-022-00591-4 · 2022 · External reference
Unresolved reference
External reference
Unresolved reference
External reference
Unresolved reference
External reference
MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces
2025 · External reference
Poet: open-ended coevolution of environments and their optimized solutions
10.1145/3321707.3321799 · 2019 · External reference
Unresolved reference
External reference
Towards end-to-end automation of ai research
10.1038/s41586-026-10265-5 · 2026 · External reference
Latent learning progress drives autonomous goal selection in human reinforcement learning
2024 · External reference
Humans monitor learning progress in curiosity-driven exploration
10.1038/s41467-021-26196-w · 2021 · External reference
Contributions of expected learning progress and perceptual novelty to curiosity-driven exploration
10.1016/j.cognition.2022.105119 · 2022 · External reference
Using games to understand the mind
10.1038/s41562-024-01878-9 · 2024 · External reference
Naturalistic reinforcement learning
10.1016/j.tics.2023.08.016 · 2024 · External reference
Unresolved reference
External reference
Unresolved reference
External reference
Socially intelligent machines that learn from humans and help humans learn
10.1098/rsta.2022.0048 · 2023 · External reference
10.31234/osf.io/2yu9e
10.31234/osf.io/2yu9e · External reference
Imagining and building wise machines: the centrality of AI metacognition
2026 · External reference
Unresolved reference
1999 · External reference
Unresolved reference
2026 · External reference
Unresolved reference
External reference
Unresolved reference
External reference
GPT-3-driven pedagogical agents to train children’s curious question-asking skills
10.1007/s40593-023-00340-7 · 2024 · External reference
Unresolved reference
External reference
Human-ai complementarity: A goal for amplified oversight
2026 · External reference
What do we learn about development from baby robots?
10.1002/wcs.1395 · ExternalCitation · doi-reference
GPT-3-driven pedagogical agents to train children’s curious question-asking skills
10.1007/s40593-023-00340-7 · ExternalCitation · doi-reference
Contributions of expected learning progress and perceptual novelty to curiosity-driven exploration
10.1016/j.cognition.2022.105119 · ExternalCitation · doi-reference
Midbrain dopamine neurons signal preference for advance information about upcoming rewards
10.1016/j.neuron.2009.06.009 · ExternalCitation · doi-reference
A goal-centric outlook on learning
10.1016/j.tics.2023.08.011 · ExternalCitation · doi-reference
Naturalistic reinforcement learning
10.1016/j.tics.2023.08.016 · ExternalCitation · doi-reference
Inpraise of folly: flexible goals and human cognition
10.1016/j.tics.2024.03.006 · ExternalCitation · doi-reference
Humans monitor learning progress in curiosity-driven exploration
10.1038/s41467-021-26196-w · ExternalCitation · doi-reference
Using games to understand the mind
10.1038/s41562-024-01878-9 · ExternalCitation · doi-reference
Towards end-to-end automation of ai research
10.1038/s41586-026-10265-5 · ExternalCitation · doi-reference
Language and culture internalization for human-like autotelic ai
10.1038/s42256-022-00591-4 · ExternalCitation · doi-reference
Goals as reward-producing programs
10.1038/s42256-025-00981-4 · ExternalCitation · doi-reference
Valuation of knowledge and ignorance in mesolimbic reward circuitry
10.1073/pnas.1800547115 · ExternalCitation · doi-reference
Socially intelligent machines that learn from humans and help humans learn
10.1098/rsta.2022.0048 · ExternalCitation · doi-reference
Intrinsically motivated reinforcement learning: an evolutionary perspective
10.1109/tamd.2010.2051031 · ExternalCitation · doi-reference
GRAIL: a goal-discovering robotic architecture for intrinsically-motivated learning
10.1109/tcds.2016.2538961 · ExternalCitation · doi-reference
The Evolution of Human Goals
10.1111/tops.70078 · ExternalCitation · doi-reference
Poet: open-ended coevolution of environments and their optimized solutions
10.1145/3321707.3321799 · ExternalCitation · doi-reference
Play, curiosity, and cognition
10.1146/annurev-devpsych-070120-014806 · ExternalCitation · doi-reference
Autotelic agents with intrinsically motivated goal-conditioned reinforcement learning: a short survey
10.1613/jair.1.13554 · ExternalCitation · doi-reference
10.31234/osf.io/2yu9e
10.31234/osf.io/2yu9e · ExternalCitation · doi-reference
What is intrinsic motivation? A typology of computational approaches
10.3389/neuro.12.006.2007 · ExternalCitation · doi-reference
ACES: generating diverse programming puzzles with autotelic language models and semantic descriptors
10.52202/079017-2160 · ExternalCitation · doi-reference
10.7551/mitpress/3115.003.0030
10.7551/mitpress/3115.003.0030 · ExternalCitation · doi-reference
