CORTEXA
← Browse
arxivcs.LGcs.AI2026-07-08

Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms

Ezgi Korkmaz

Starting from the utilization of deep neural networks to approximate the state-action value function that led to winning one of the most challenging games, to algorithmic advancements that allowed solving problems without even explicitly stating the rules of the challenge at hand, reinforcement learning research has been the center of remarkable scientific progress for the past decade. In this paper, we focus on the key ingredients of this research progress and we analyze the canonical evaluation and design paradigms in reinforcement learning. We introduce the theoretical foundations of scaling laws in reinforcement learning and show that the asymptotic performance of reinforcement learning algorithms does not have a monotone relationship between performance rankings and data-regimes. We conduct large-scale experiments and our results demonstrate that a line of reinforcement learning research under the canonical design and evaluation paradigms resulted in incorrect conclusions. Our analysis and results provide a core analysis on scaling, capacity and complexity of deep reinforcement learning.

View free PDFSource page

Related papers

arxivcs.CVcs.AIcs.LG2026-07-24

CARDIAG: A Dense Segment Classification Benchmark of Deep Learning Architectures for Coronary Angiography

Dominik Bernard Lau, Hubert Malinowski, Jerzy Szyjut, Adam Brzeski, Tomasz Dziubich, Radosław Targoński, et al.

Accurate pixel-level classification of coronary angiograms is critical for cardiovascular disease assessment, yet the field lacks standardized evaluation protocols. In this work we demonstrate a new benchmark for the assessment of deep learning models which densely classify pixel…

View free PDFSource page
arxivcs.LGcs.AIcs.CL2026-07-24

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning

Shujin Wu, Cheng Qian, Xiusi Chen, Heng Ji

Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains. We hypothesize that the success of such evolution frameworks hinges on meta-skills, such as self-reflection with environment feedback,…

View free PDFSource page
arxivquant-phcs.AIcs.LG2026-07-24

Quantum Spectral Model: Data Reuploading with Input-Conditioned Frequency Support

Peiyong Wang, Udaya Parampalli, Casey R. Myers

A central design principle in modern machine learning and artificial intelligence is to align a model's inductive bias with the structure of its input data. For matrix-valued inputs, relevant matrix-level relationships can be characterised through spectral values and spectral sub…

View free PDFSource page
arxivcs.AIcs.LG2026-07-31

DungeonBench: A Benchmark for Rules-Rich Tactical Reasoning in Dungeons & Dragons Combat

Ismayil Ismayilov, Atakan Kara, Kaan Oktay

Games and simulators make valuable benchmarks by turning decisions into measurable outcomes, but many current suites under-test rules-rich tactical reasoning: the ability to choose well when geometry, timing, resources, objectives, and rule interactions all matter at once. We int…

View free PDFSource page
arxivcs.LGcs.AI2026-07-23

Relative Value Learning

Marc Höftmann, Jan Robine, Stefan Harmeling

In reinforcement learning, critics typically estimate absolute state values $V(s)$, estimating how good a particular situation is in isolation. However, it turns out that only differences in value are relevant for control. Motivated by this, we propose Relative Value Learning (RV…

View free PDFSource page
arxivcs.LGcs.AI2026-07-24

Optimization of time-consuming experimental conditions using pseudo-experimental data guided by adaptive polynomial regression

Hirotaka Sugawara, Yujin Taguchi, Kei Minagawa, Yusuke Hiki, Takashi Morikura, Akira Funahashi

Bayesian optimization (BO) is an optimization method that sequentially proposes the next candidate explainable variables for optimizing target variables by balancing exploration and exploitation. BO is often used under a limited evaluation budget, such as hyperparameter tuning of…

View free PDFSource page