Continuous Homeostatic Reinforcement Learning for Self-Regulated Autonomous Agents

no code implementations • 14 Sep 2021 • Hugo Laurençon, Charbel-Raphaël Ségerie, Johann Lussange, Boris S. Gutkin

The recently introduced homeostatic regulated reinforcement learning theory (HRRL), by defining within the framework of reinforcement learning a reward function based on the internal state of the agent, makes the link between the theories of drive reduction and reinforcement learning.

Decision Making Learning Theory +2

Spiking and saturating dendrites differentially expand single neuron computation capacity

no code implementations • NeurIPS 2012 • Romain Cazé, Mark Humphries, Boris S. Gutkin

Third, we show that one cannot use a DNF-based architecture with saturating dendrites.

A Reinforcement Learning Theory for Homeostatic Regulation

no code implementations • NeurIPS 2011 • Mehdi Keramati, Boris S. Gutkin

Reinforcement learning models address animal's behavioral adaptation to its changing "external" environment, and are based on the assumption that Pavlovian, habitual and goal-directed responses seek to maximize reward acquisition.

Learning Theory reinforcement-learning +1