CORTEXA
← Browse
arxivcs.LGcs.AI2026-06-25

Heavy-Ball Q-Learning with Residual Weighting Correction

Donghwan Lee

This paper proposes a corrected heavy-ball Q-learning method for reinforcement learning (RL) and establishes convergence of its deterministic mean dynamics. It also identifies conditions under which the method is theoretically guaranteed to converge faster than standard Q-learning. The same construction is then extended to Q-learning with linear function approximation, where analogous convergence and acceleration statements are derived for the corresponding corrected fixed point. The sampled stochastic versions are treated through conditional-mean recursions and, in the stated linear-function-approximation setting, finite-time bounds. The analysis is based on a switched linear system (SLS) representation of Q-learning algorithms and on the joint spectral radius (JSR) of the associated switching families. This SLS viewpoint is not commonly used in standard analyses of Q-learning, and it provides a complementary framework and new insight into how heavy-ball momentum can accelerate Q-learning.

View free PDFSource page

Related papers

arxivcs.LGcs.AI2026-07-24

MA-DAR: Manifold-Aligned Dynamic Adaptive Routing for Continual Temporal Knowledge Graph Reasoning

Xiangjun Shi, Chong Mu, Jinchuan Zhang, Lizong Zhang, Yuefeng He, Shang Liu

Continual temporal knowledge graph (TKG) reasoning aims to continuously incorporate newly emerging facts while preserving previously acquired knowledge. Replay-based continual learning has achieved promising performance by revisiting historical representations. However, existing…

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

Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation

Quazi Ishtiaque Mahmud, Nesreen K. Ahmed, Ali Jannesari

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful technique to enhance the reasoning capacity of LLMs for optimized code generation. However, existing RLVR approaches primarily rely on outcome-based signals such as correctness and speedup, overlookin…

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

From Perturbation Correction to Geometry-Aware Sampling: Sharpness-Guided Equilibrium Sampling for Balanced Flat Minima in Long-Tailed Learning

Jiaxin Deng, Junbiao Pang

Long-tailed learning couples two sources of poor generalization: head classes dominate training exposure, while under-represented classes often converge to sharper regions of the loss landscape. Conventional re-sampling addresses the former without considering geometry, whereas e…

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
arxivcs.LGcs.AI2026-07-23

Mean-to-Score Discrete Diffusion: Posterior-Mean Denoisers for Score Entropy

Jingyuan Li, Xiaoyi Jiang, Yixuan Jiang, Wei Liu, Yi Zhu, Zuoqiang Shi, et al.

Score Entropy Discrete Diffusion (SEDD) parameterizes discrete reverse processes with unconstrained positive score ratios. While positivity guarantees nonnegative reverse jump rates, it does not ensure Bayes realizability: ratios at a noisy state need not be jointly induced by an…

View free PDFSource page
arxivcs.AIcs.LGcs.MA2026-07-24

TRACE-ROUTER: Task-Consistent and Adaptive Online Routing for Agentic AI

Ritik Raj, Souvik Kundu, Sarbartha Banerjee, Dheemanth Joshi, Ishita Vohra, Tushar Krishna

Routing to select large language models (LLMs) with different cost-quality trade-offs has become a fundamental deployment feature of enterprise AI. Existing routers, primarily make independent routing decisions for each LLM call. However, agentic applications execute as long-hori…

View free PDFSource page