Life-inspired Interoceptive Artificial Intelligence for Autonomous and Adaptive Agents
Not on the map. Why?
Abstract (arXiv)
Building autonomous -- i.e., choosing goals based on one's needs -- and adaptive -- i.e., surviving in ever-changing environments -- agents has been a holy grail of artificial intelligence (AI). A living organism is a prime example of such an agent, offering important lessons about adaptive autonomy. Here, we focus on interoception, a process of monitoring one's internal environment to keep it within certain bounds, which underwrites the survival of an organism. To develop AI with interoception, we need to factorize the state variables representing internal environments from external environments and adopt life-inspired mathematical properties of internal environment states. This paper offers a new perspective on how interoception can help build autonomous and adaptive agents by integrating the legacy of cybernetics with recent advances in theories of life, reinforcement learning, and neuroscience.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 27 of its 187 references that are in the map. First posted on arXiv 12 Sep 2023.
Builds on
27 of 187 references.
References · 27
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
- 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 382
- 2016Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivationcited by 286
- 2018Large-Scale Study of Curiosity-Driven Learningcited by 280
- 2020Towards Continual Reinforcement Learning: A Review and Perspectivescited by 274
- 2020Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Surveycited by 85
- 2013Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizationscited by 70
- 2019Deep Active Inference as Variational Policy Gradientscited by 53
- 2020Reinforcement Learning through Active Inferencecited by 47
- 2018Cognitive computational neurosciencecited by 43
15 more
- 2020On the Relationship Between Active Inference and Control as Inferencecited by 42
- 2021Context-Aware Safe Reinforcement Learning for Non-Stationary Environmentscited by 33
- 2022The free energy principle made simpler but not too simplecited by 27
- 2018Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Explorationcited by 23
- 2017Emotion in Reinforcement Learning Agents and Robots: A Surveycited by 21
- 2022Path integrals, particular kinds, and strange thingscited by 20
- 2018Introducing Neuromodulation in Deep Neural Networks to Learn Adaptive Behaviourscited by 16
- 2022Testing Stationarity and Change Point Detection in Reinforcement Learningcited by 12
- 2021Context Meta-Reinforcement Learning via Neuromodulationcited by 11
- 2017Diffusion-based neuromodulation can eliminate catastrophic forgetting in simple neural networkscited by 10
- 2020Active Inference or Control as Inference? A Unifying Viewcited by 9
- 2018Self-Organization and Artificial Life: A Reviewcited by 3
- 2016On Reward Function for Survivalcited by 2
- 2019Neural dynamics of emotion and cognition: from trajectories to underlying neural geometrycited by 2
- 2021Continuous Homeostatic Reinforcement Learning for Self-Regulated Autonomous Agentscited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.