arXiv Machine Learning
RL-ABC: Reinforcement Learning for Accelerator Beamline Control
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jul 24
Classifier-pruned Bayesian optimization for particle accelerator tuning: Exploring temporally structured manifold of 6D beam phase space
arXiv:2412. 01748v2 Announce Type: replace Abstract: Complex dynamical systems, such as particle accelerators, often require intricate and time-consuming tuning procedures to achieve optimal performance.
arXiv Machine Learning
Jul 1
Deep Reinforcement Learning for Spacecraft Attitude Control During Atmospheric Re-Entry
arXiv:2606. 31291v1 Announce Type: new Abstract: Deep reinforcement learning has the potential to solve attitude control problems more adaptively, precisely, and robustly by handling nonlinear dynamics, uncertainties, and failure cases more effectively than traditional attitude control approaches.
arXiv AI
Jun 30
Agile Reinforcement Learning through Separable Neural Architecture and Applications
arXiv:2601. 23225v2 Announce Type: replace-cross Abstract: Deep reinforcement learning (RL) is increasingly deployed in resource-constrained environments, yet go-to function approximators - multilayer perceptrons (MLPs) - are often parameter-inefficient due to an imperfect inductive bias for the smooth structure of many value functions.
arXiv Machine Learning
Jun 5
Alpha-RTL: Test-Time Training for RTL Hardware Optimization
arXiv:2606. 05253v1 Announce Type: new Abstract: Large language models (LLMs) have shown increasing promise in generating functionally correct register-transfer-level (RTL) hardware designs.
arXiv AI
Jun 9
HARBOR: A Harness Framework for Agentic Robot Reinforcement Learning
arXiv:2606. 08610v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a powerful paradigm for robot learning, particularly in sim-to-real settings, but its broader adoption remains limited by the engineering pipeline surrounding the algorithms.
arXiv Machine Learning
Aug 19
Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements
Agentic ESOpt proposes using evolution strategies (ES) instead of reinforcement learning to fine‑tune large language‑model agents for long‑horizon tasks. ES offers model scalability, flexibility, and better long‑horizon credit assignment, enabling full‑parameter optimization with minimal GPU memory. The framework samples parameter perturbations, evaluates agents with rewards, and updates online, achieving notable performance gains on WebArena‑Lite and in test‑time prompt‑parameter co‑evolution.