Tag
This paper introduces V-Simba, a visual RL architecture that adds normalization layers and pointwise convolutions to improve sample efficiency and stability. It matches or outperforms state-of-the-art methods across DMC, Adroit, and Meta-World benchmarks while being more computationally efficient than DrQ-v2.
Proposes a closed-loop evolutionary algorithm that guides LLMs to generate complete, executable PINN configurations, reducing mean-squared error on a one-dimensional multiscale wave equation.