CORTEXA
← Browse
arxivcs.LG2026-07-20

Information-Based Exploration via Random Features for Reinforcement Learning

Waris Radji, Odalric-Ambrym Maillard

Representation learning has enabled classical exploration strategies to be extended to deep Reinforcement Learning (RL), but often makes algorithms more complex and theoretical guarantees harder to establish. We introduce Random Feature Information Gain (RFIG), grounded in Bayesian kernel methods theory, which uses random Fourier features to approximate information gain and compute exploration bonuses in non-countable spaces. We provide error bounds on information gain approximation and avoid the black-box aspects of neural network-based uncertainty estimation, for optimism-based exploration. We present practical details that make RFIG scalable to deep RL scenarios, enabling smooth integration into standard deep RL algorithms. Experimental evaluation across diverse control and navigation tasks demonstrates that RFIG achieves competitive performance with well-established deep exploration methods while offering superior theoretical interpretation.

View free PDFSource page

Related papers

arxivcs.LG2026-07-31

Sample Efficient Hierarchical Reinforcement Learning via Best Policy Identification

Anders Jonsson, Emilie Kaufmann, Gianmarco Tedeschi, Lorenzo Steccanella

We present HBPI-UCRL, a model-based algorithm for hierarchical reinforcement learning (HRL) that learns high-level and low-level policies in parallel. HBPI-UCRL exploits the fact that a high-level transition corresponds to a multi-step transition at the low level. We introduce tw…

View free PDFSource page
arxivcs.LG2026-07-24

Integrated Order Dispatching and Routing for Last-Mile Pickup via Deep Reinforcement Learning

Yida Xu, Zhaofang Mao, Yuheng Miao, Jiaxin Zhang, Yiting Sun

In recent years, the growing complexity of last-mile pickup operations has increased the need for fast and accurate decision-making on logistics platforms. This challenge is fundamentally driven by two key and tightly coupled decision-making processes: order dispatching and routi…

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

TOUR: A Trajectory-Level Unlearning Benchmark for Offline Reinforcement Learning

Chaofan Pan, Lingfei Ren, Xiangyu Jiang, Yanhua Li, Xuemei Cao, Xiangkun Wang, et al.

Offline Reinforcement Learning (RL) agents are trained on fixed behavioral trajectories, which makes trajectory-level deletion important when selected data must be removed after training. Evaluating such deletion is difficult because a lower membership score can reflect trajector…

View free PDFSource page
arxivcs.LGphysics.comp-ph2026-07-24

Latent PDE mapping for efficient physics-informed learning across geometries with limited data

Ingvild Askim Adde, Mary M. Maleckar, Gabriel Balaban

In this study, we introduce latent PDE mapping, a broadly applicable physics-informed learning technique designed to enable efficient geometric generalization with sparse training data. Latent PDE mapping pulls back geometry-specific PDE residuals and boundary conditions to a pre…

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