Training Reinforcement Learning Agents and Humans with Difficulty-Conditioned Generators
Keywords: UED, Item Response Theory
TL;DR: We deploy an Item Response Theory-based model to generate curricula and train both humans and RL Agents
Abstract: We introduce Parameterized Environment Response Model (PERM), a method for training both Reinforcement Learning (RL) Agents and human learners in parameterized environments by directly modeling difficulty and ability. Inspired by Item Response Theory (IRT), PERM aligns environment difficulty with individual ability, creating a Zone of Proximal Development-based curriculum. Remarkably, PERM operates without real-time RL updates and allows for offline training, ensuring its adaptability across diverse students. We present a two-stage training process that capitalizes on PERM's adaptability, and demonstrate its effectiveness in training RL agents and humans in an empirical study.
Submission Number: 35
Loading