CORTEXA
← Browse
arxivcs.LGcs.AI2026-06-30

AETDICE: Unified Framework and Offline Optimization for Nonlinear Multi-Objective RL

Woosung Kim, Youngjun Suh, Jinho Lee, Jongmin Lee, Byung-Jun Lee

Optimizing nonlinear preferences in multi-objective reinforcement learning (MORL) is essential for capturing complex trade-offs like risk aversion or fairness. However, such non-linearity has historically bifurcated nonlinear MORL objectives into two distinct paradigms: Scalarized Expected Return (SER) and Expected Scalarized Return (ESR). While SER requires global-level optimization and ESR requires non-Markovian policies, leading to fragmented optimization strategies, we bridge this divide through the Aggregation-Expectation-Transformation (AET) framework. By unifying both criteria through a tripartite decomposition of scalarization, AET provides a principled foundation for general nonlinear MORL. Building on this framework, we propose AETDICE, a tractable offline RL algorithm for AET objectives. By utilizing DICE-style density-ratio estimation in an augmented state space, AETDICE enables sample-based optimization from static datasets. Our framework resolves long-standing barriers and captures respective trade-offs induced by AET framework, which existing methods fail to address.

View free PDFSource page

Related papers

arxivcs.LGcs.AI2026-07-10

Semantic Pareto-DQN: A Multi-Objective Reinforcement Learning Framework for Financial Anomaly Detection

Cláudio Lúcio do Val Lopes, Lucca Machado da Silva

Financial anomaly detection suffers from extreme class imbalance, causing traditional single-objective algorithms to exhibit ``fraud collapse'', defaulting to the majority class and failing to balance anomaly interdiction with customer friction. To overcome this without distortiv…

View free PDFSource page
arxivcs.LGcs.AI2026-07-31

MOT-SR: Multi-Objective Tool-Augmented Scientific Equation Discovery with Large Language Models

Boxiao Wang, Runxiang Wang, Kai Li, Chongming Li, Zhiwei Chen, Yifan Zhang, et al.

Symbolic Regression (SR) aims to discover analytical equations from observational data and plays a central role in scientific modeling. While recent Large Language Model (LLM) based approaches show promise, they face two limitations. First, they lack data analysis mechanisms for…

View free PDFSource page
arxivcs.LGcs.AIcs.CV2026-07-02

Population-Based Multi-Objective Training of Discriminators for Semi-Supervised GANs

Francisco Sedeño, Francisco Chicano, Jamal Toutouh

Semi-supervised generative adversarial networks (SSL-GANs) can exploit large unlabeled datasets while retaining a classifier in the discriminator, but their training is often unstable. This paper proposes a population-based evolutionary training strategy in which discriminator le…

View free PDFSource page
arxivcs.LGcs.AImath.OC2026-07-07

Deep Reinforcement Learning for Reliability Based Bi-Objective Portfolio Optimization

Sounaq Das, Tanmay Sen, Raghu Nandan Sengupta, Aditya Gupta

Portfolio optimization under uncertainty is inherently a multi-objective decision problem involving complex interactions among return, risk, market dynamics, and practical investment constraints. Existing reliability based portfolio optimization approaches primarily rely on stati…

View free PDFSource page
arxivcs.LGcs.AIeess.SY2026-06-30

Preference-Conditioned Multi-Objective Reinforcement Learning for Runtime-Tunable Transit Signal Priority

Philip-Roman Adam, Stefanie Schmidtner

Transit signal priority (TSP) requires balancing competing objectives: reducing bus delay while limiting adverse impacts on non-bus traffic and avoiding extreme waits for a subset of vehicles. Existing reinforcement-learning (RL) approaches to TSP typically encode transit-aware f…

View free PDFSource page