2 papers
stat.ML2025
Curiosity-Driven Development of Action and Language in Robots Through Self-Exploration
Theodore Jerome Tinker, Kenji Doya, Jun Tani
Infants acquire language with generalization from minimal experience, whereas large language models require billions of training tokens. What underlies efficient development in hum…
cs.LG2024
Intrinsic Rewards for Exploration without Harm from Observational Noise: A Simulation Study Based on the Free Energy Principle
Theodore Jerome Tinker, Kenji Doya, Jun Tani
In Reinforcement Learning (RL), artificial agents are trained to maximize numerical rewards by performing tasks. Exploration is essential in RL because agents must discover informa…