← Back to all news
arXiv Machine Learning By Gabriel Nova, Stephane Hess, Sander van Cranenburgh

Delphos: A reinforcement learning framework for assisting discrete choice model specification

Read the original on arXiv Machine Learning →

Delphos is a deep reinforcement learning framework designed to aid the specification of discrete choice models. It treats model specification as a sequential decision-making task, where an agent selects modeling actions—such as adding constants, choosing taste parameters, applying transformations, or including interactions—to generate candidate models. Each candidate is estimated and evaluated using a reward function that reflects statistical fit and behavioral expectations, and a Deep Q-Network learns which sequences of decisions lead to high-quality models, as demonstrated on simulated and empirical datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 17

Multitask Reinforcement Learning for Assisting Choice Model Specification

Delphos is a multitask reinforcement learning framework that automates discrete choice model specification by treating it as a sequential decision-making problem. It learns transferable specification strategies across multiple transport choice datasets using a DeepSet‑Q architecture, enabling a shared policy to adapt to varying variable sets. Trained on nine datasets, Delphos outperforms single‑task agents, and when applied to unseen Swissmetro and Decisions datasets, it quickly identifies competitive specifications with higher log‑likelihoods than existing methods.

By Gabriel Nova, Stephane Hess, Sander Van Cranenburgh
agentsreinforcement-learning
More like this →
arXiv AI
Sep 3

Propose to Learn, Learn to Propose: Evaluability-Aware Assistance under Bounded Rationality

The paper introduces ProSE, a framework for AI assistants that generate proposals while considering users’ bounded rationality and evaluability constraints. It proposes a KL‑regularised bounded‑rational binary response model and a depth‑2 Bayes‑adaptive planner, “ProSE‑Plan,” which scores proposals by expected responses and resulting belief updates. Experiments on graph simulations show that “ProSE‑Plan” outperforms evaluability‑unaware and myopic baselines, especially when evaluation cost is high, and that informative probes are crucial for effective assistance.

By Yifan Zhu, Sammie Katt, Samuel Kaski
benchmarks
More like this →