Training Reinforcement Learning Agents and Humans with Difficulty-Conditioned Generators
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.
Cite
Text
Tio and Varakantham. "Training Reinforcement Learning Agents and Humans with Difficulty-Conditioned Generators." NeurIPS 2023 Workshops: ALOE, 2023.Markdown
[Tio and Varakantham. "Training Reinforcement Learning Agents and Humans with Difficulty-Conditioned Generators." NeurIPS 2023 Workshops: ALOE, 2023.](https://mlanthology.org/neuripsw/2023/tio2023neuripsw-training/)BibTeX
@inproceedings{tio2023neuripsw-training,
title = {{Training Reinforcement Learning Agents and Humans with Difficulty-Conditioned Generators}},
author = {Tio, Sidney and Varakantham, Pradeep},
booktitle = {NeurIPS 2023 Workshops: ALOE},
year = {2023},
url = {https://mlanthology.org/neuripsw/2023/tio2023neuripsw-training/}
}