Emergence of Implicit World Models from Mortal Agents
On the map: World models → World models for language agents
Abstract (arXiv)
We discuss the possibility of world models and active exploration as emergent properties of open-ended behavior optimization in autonomous agents. In discussing the source of the open-endedness of living things, we start from the perspective of biological systems as understood by the mechanistic approach of theoretical biology and artificial life. From this perspective, we discuss the potential of homeostasis in particular as an open-ended objective for autonomous agents and as a general, integrative extrinsic motivation. We then discuss the possibility of implicitly acquiring a world model and active exploration through the internal dynamics of a network, and a hypothetical architecture for this, by combining meta-reinforcement learning, which assumes domain adaptation as a system that achieves robust homeostasis.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 6 of its 51 references that are in the map. First posted on arXiv 19 Nov 2024.
Builds on
6 of 51 references.
References · 6
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2023Mastering Diverse Domains through World Modelscited by 1,253
- 2015Illuminating search spaces by mapping elitescited by 425
- 2016Learning to reinforcement learncited by 377
- 2018Large-Scale Study of Curiosity-Driven Learningcited by 280
- 2024Discovering Sensorimotor Agency in Cellular Automata using Diversity Searchcited by 9
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light
- 2026The Artificial Experimentalist: Discovery and Control of Self-Organizing Phenomena with Autotelic Reinforcement Learning
- 2024Active Inference as a Model of Agency
- 2026Intrinsic Motivation in Reinforcement Learning: A Research Agenda for Adaptive Self-Organisation
- 2025One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
- 2019Bayesian policy selection using active inference
- 2025World Models Unlock Optimal Foraging Strategies in Reinforcement Learning Agents
- 2025Intrinsic Goals for Autonomous Agents: Model-Based Exploration in Virtual Zebrafish Predicts Ethological Behavior and Whole-Brain Dynamics