LLM Voting: Human Choices and AI Collective Decision Making

no code implementations • 31 Jan 2024 • Joshua C. Yang, Marcin Korecki, Damian Dailisan, Carina I. Hausladen, Dirk Helbing

This paper investigates the voting behaviors of Large Language Models (LLMs), particularly OpenAI's GPT4 and LLaMA2, and their alignment with human voting patterns.

Decision Making

Dynamic value alignment through preference aggregation of multiple objectives

no code implementations • 9 Oct 2023 • Marcin Korecki, Damian Dailisan, Cesare Carissimo

The development of ethical AI systems is currently geared toward setting objective functions that align with human objectives.

Q-Learning

Deep-learned orthogonal basis patterns for fast, noise-robust single-pixel imaging

no code implementations • 18 May 2022 • Ritz Ann Aguilar, Damian Dailisan

Single-pixel imaging (SPI) is a novel, unconventional method that goes beyond the notion of traditional cameras but can be computationally expensive and slow for real-time applications.

Adaptive Coordination Offsets for Signalized Arterial Intersections using Deep Reinforcement Learning

no code implementations • 6 Aug 2020 • Keith Anshilo Diaz, Damian Dailisan, Umang Sharaf, Carissa Santos, Qijian Gan, Francis Aldrine Uy, May T. Lim, Alexandre M. Bayen

Here, we propose a deep RL framework that dynamically adjusts offsets based on traffic states and preserves the planned phase timings and order derived from model-based methods.

reinforcement-learning Reinforcement Learning (RL)