Then satisfies inequation 8 >0, 8 6 , ( )>1 ( ) +1 .

Unlike traditional models, e.g., MLP,these architectures mapscalar valuesofnumerical features tohigh-dimensional embeddings before mixing them inthemain backbone.

In recent years, we have witnessed tremendous progress in deep reinforcement learning(RL)fortaskssuchasGo,Chess,videogames,androbotcontrol.

The AlphaZero framework provides a standard way of combining Monte Carlo planning with prior knowledge provided by a previously trained policy-value neural network. AlphaZero usually assumes that the environment on which the neural network was trained will not change at test time, which constrains its applicability. In this paper, we analyze the problem of deploying AlphaZero agents in potentially changed test environments and demonstrate how the combination of simple modifications to the standard framework can significantly boost performance, even in settings with a low planning budget available. The code is publicly available on GitHub3.

Sparse autoencoders are a standard tool for uncovering interpretable latent representations in neural networks. Yet, their interpretation depends on the inputs, making their isolated study incomplete. Polynomials offer a solution; they serve as algebraic primitives that can be analysed without reference to input and can describe structures ranging from linear concepts to complicated manifolds. This work uses bilinear autoencoders to efficiently decompose representations into quadratic polynomials. We discuss improvements that induce importance ordering, clustering, and activation sparsity. This is an initial step toward nonlinear yet analysable latents through their algebraic properties.

Accurate localization represents a fundamental challenge in robotic navigation. Traditional methodologies, such as Lidar or QR-code-based systems, suffer from inherent scalability and adaptability constraints, particularly in complex environments. In this work, we propose an innovative localization framework that harnesses flooring characteristics by employing graph-based representations and Graph Convolutional Networks (GCNs). Our method uses graphs to represent floor features, which helps localize the robot more accurately ( 0. 64 cm error) and more efficiently than comparing individual image features. Additionally, this approach successfully addresses the kidnapped robot problem in every frame without requiring complex filtering processes.