From 2fe41abf1313dc24c183241674f2ae8e0464d653 Mon Sep 17 00:00:00 2001 From: Kristian Kersting Date: Sun, 29 Dec 2024 16:58:19 +0100 Subject: [PATCH] Update references.bib --- references.bib | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/references.bib b/references.bib index c5a0644..aaea0df 100644 --- a/references.bib +++ b/references.bib @@ -3,7 +3,7 @@ @inproceedings{natarajan2025aaai title={Human-in-the-loop or AI-in-the-loop? Automate or Collaborate?}, url={https://arxiv.org/pdf/2412.14232}, Note={Human-in-the-loop (HIL) systems have emerged as a promising approach for combining the strengths of data-driven machine learning models with the contextual understanding of human experts. However, a deeper look into several of these systems reveals that calling them HIL would be a misnomer, as they are quite the opposite, namely AI-in-the-loop (AI2L) systems, where the human is in control of the system, while the AI is there to support the human. We argue that existing evaluation methods often overemphasize the machine (learning) component's performance, neglecting the human expert's critical role. Consequently, we propose an AI2L perspective, which recognizes that the human expert is an active participant in the system, significantly influencing its overall performance. By adopting an AI2L approach, we can develop more comprehensive systems that faithfully model the intricate interplay between the human and machine components, leading to more effective and robust AI systems.}, - booktitle={Proceedings of the AAAI Conference on Artificial Intelligence}, + booktitle={Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)}, author={Sriraam Natarajan and Saurabh Mathur and Sahil Sidheekh and Wolfgang Stammer and Kristian Kersting}, year={2025}, pages={}, @@ -886,7 +886,7 @@ @inproceedings{derstroff2023peer Note={Peer learning is a novel high-level reinforcement learning framework for agents learning in groups. While standard reinforcement learning trains an individual agent in trial-and-error fashion, all on its own, peer learning addresses a related setting in which a group of agents, i.e., peers, learns to master a task simultaneously together from scratch. Peers are allowed to communicate only about their own states and actions recommended by others: "What would you do in my situation?". Our motivation is to study the learning behavior of these agents. We formalize the teacher selection process in the action advice setting as a multi-armed bandit problem and therefore highlight the need for exploration. Eventually, we analyze the learning behavior of the peers and observe their ability to rank the agents’ performance within the study group and understand which agents give reliable advice. Further, we compare peer learning with single agent learning and a state-of-the-art action advice baseline. We show that peer learning is able to outperform single-agent learning and the baseline in several challenging discrete and continuous OpenAI Gym domains. Doing so, we also show that within such a framework complex policies from action recommendations beyond discrete action spaces can evolve.}, number={10}, - booktitle={Proceedings of the AAAI Conference on Artificial Intelligence}, + booktitle={Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)}, author={Cedric Derstroff and Mattia Cerrato and Jannis Brugger and Jan Peters and Stefan Kramer}, year={2024}, month={Mar.}, pages={11766-11774}, Anote = {./images/peerlearning_paper.png},