Linking homeostasis to reinforcement learning: internal state control of motivated behavior

For living beings, survival depends on effective regulation of internal physiological states through motivated behaviors. In this perspective, we propose homeostatically regulated reinforcement learning (HRRL) as a framework to describe biological agents that optimize internal states via learned predictive control strategies, integrating biological principles with computational learning. We show that HRRL inherently produces multiple behaviors such as risk aversion, anticipatory regulation, and adaptive movement, aligning with observed biological phenomena. Its extension to deep reinforcement learning enables autonomous exploration, hierarchical behavior, and potential real-world robotic applications. We argue further that HRRL offers a biologically plausible foundation for understanding motivation, learning, and decision-making, with broad implications for artificial intelligence (AI), neuroscience, and understanding the causes of psychiatric disorders, ultimately advancing our understanding of adaptive behavior in complex environments. • The Homeostatically Regulated Reinforcement Learning (HRRL) explains adaptive stability. • In HRRL, reward is defined as drive reduction from homeostatic deviation. • HRRL explains apparent irrationality through properties of the underlying drive. • HRRL offers an embodied framework for AI, mental disorders, and cognitive theory.