Humans can perform complex tasks with long-term objectives by planning, reasoning, and forecasting outcomes of actions. For embodied agents to achieve similar capabilities, they must gain knowledge of the environment transferable to novel scenarios with a limited budget of additional trial and error. Learning-based approaches, such as deep RL, can discover and take advantage of inherent regularities and characteristics of the application domain from data, and continuously improve their performances, however at a cost of large amounts of training data. This thesis explores the development of data-driven techniques for spatial reasoning and planning tasks, focusing on enhancing learning efficiency, interpretability, and transferability across novel scenarios. Four key contributions are made. 1) CALVIN, a differential planner that learns interpretable models of the world for long-term planning. It successfully navigated partially observable 3D environments, such as mazes and indoor rooms, by learning the rewards and state transitions from expert demonstrations. 2) SOAP, an RL algorithm that discovers options unsupervised for long-horizon tasks. Options segment a task into subtasks and enable consistent execution of the subtask. SOAP showed robust performances on history-conditional corridor tasks as well as classical benchmarks such as Atari. 3) LangProp, a code optimisation framework using LLMs to solve embodied agent problems that require reasoning by treating code as learnable policies. The framework successfully generated interpretable code with comparable or superior performance to human-written experts in the CARLA autonomous driving benchmark. 4) Voggite, an embodied agent with a vision-to-action transformer backend that solves complex tasks in Minecraft. It achieved third place in the MineRL BASALT Competition by identifying action triggers to segment tasks into multiple stages.

Medical image analysis using deep learning frameworks has advanced healthcare by automating complex tasks, but many existing frameworks lack flexibility, modularity, and user-friendliness. To address these challenges, we introduce Yucca, an open-source AI framework available at https://github.com/Sllambias/yucca, designed specifically for medical imaging applications and built on PyTorch and PyTorch Lightning. Yucca features a three-tiered architecture: Functional, Modules, and Pipeline, providing a comprehensive and customizable solution. Evaluated across diverse tasks such as cerebral microbleeds detection, white matter hyperintensity segmentation, and hippocampus segmentation, Yucca achieves state-of-the-art results, demonstrating its robustness and versatility. Yucca offers a powerful, flexible, and user-friendly platform for medical image analysis, inviting community contributions to advance its capabilities and impact.

YAMLE: Yet Another Machine Learning Environment is an open-source framework that facilitates rapid prototyping and experimentation with machine learning (ML) models and methods. The key motivation is to reduce repetitive work when implementing new approaches and improve reproducibility in ML research. YAMLE includes a command-line interface and integrations with popular and well-maintained PyTorch-based libraries to streamline training, hyperparameter optimisation, and logging. The ambition for YAMLE is to grow into a shared ecosystem where researchers and practitioners can quickly build on and compare existing implementations.

Meta, previously known as Facebook, has made significant contributions to the world of artificial intelligence through its AI research division, Meta AI. One of its latest AI models is CICERO (Compressive Information-Conditional Entropy Reinforcement Optimization), which is designed for efficient information extraction from large datasets. In this article, we will delve into the frameworks and tools that make CICERO possible, exploring the underlying processes, best practices, and "how-to" guides for each component, complete with code snippets to help you get started. PyTorch is an open-source machine learning framework developed by Meta AI, which is widely used for developing deep learning models, including CICERO. It offers a flexible and efficient platform for building and training neural networks.

Lightning Fabric is a new, open-source library that allows you to quickly and easily scale models while maintaining full control over your training loop. In the past, getting PyTorch code to run efficiently on GPUs and scaling it up to many machines and large datasets was possible with PyTorch Lightning. As time went on, however, we became aware of the need to provide a scaling option that landed somewhere between a raw deep learning framework like PyTorch on the one hand, and a high-level, feature-rich framework like PyTorch Lightning. Lightning Fabric is just that. While PyTorch Lightning provides many features to save time and improve readability and collaboration, there are complex use cases where full control over the training loop is needed.

Koila solves CUDA error: out of memory error painlessly. Fix it with just one line of code, and forget it. To use it, download release v0.1.1 here.* Automatically accumulates gradients when batch sizes are too large. Lazily evaluates PyTorch code to save computing power.

MLOps is essential for companies both large and small that build products and services powered by AI. Given the wide variety of tools and platforms that aim to solve different parts of the machine learning lifecycle, choosing between them isn't always easy. Building a machine learning training and deployment pipeline is a fractured experience from the get-go. Below, we'll go through Lightning's unified platform for training and deploying machine learning models in production. Lightning (by the same people who built PyTorch Lightning) is a platform that augments the capabilities of PyTorch Lightning beyond training, into serving, deploying, monitoring, and data engineering.

MLPerf training times represent the state of the art in machine learning performance, in which AI industry leaders publish their best training times for a set of common machine learning models. But optimizing for training speed means these models are often complex, and difficult to move to practical applications. Last year, we published SageMakerCV, a collection of computer vision models based on MLPerf, but with added flexibility and optimization for use on Amazon SageMaker. The recently published MLPerf 2.0 adds a series of new optimizations. In this blog, discuss those optimizations, and how we can use PyTorch Lightning and the SageMaker Debugger to further improve training performance and flexibility.

We present the Open MatSci ML Toolkit: a flexible, self-contained, and scalable Python-based framework to apply deep learning models and methods on scientific data with a specific focus on materials science and the OpenCatalyst Dataset. Our toolkit provides: 1. A scalable machine learning workflow for materials science leveraging PyTorch Lightning, which enables seamless scaling across different computation capabilities (laptop, server, cluster) and hardware platforms (CPU, GPU, XPU). 2. Deep Graph Library (DGL) support for rapid graph neural network prototyping and development. By publishing and sharing this toolkit with the research community via open-source release, we hope to: 1. Lower the entry barrier for new machine learning researchers and practitioners that want to get started with the OpenCatalyst dataset, which presently comprises the largest computational materials science dataset. 2. Enable the scientific community to apply advanced machine learning tools to high-impact scientific challenges, such as modeling of materials behavior for clean energy applications. We demonstrate the capabilities of our framework by enabling three new equivariant neural network models for multiple OpenCatalyst tasks and arrive at promising results for compute scaling and model performance.

The following paper is a reproducibility report for "Social NCE: Contrastive Learning of Socially-aware Motion Representations" {\cite{liu2020snce}} published in ICCV 2021 as part of the ML Reproducibility Challenge 2021. The original code was made available by the author \footnote{\href{https://github.com/vita-epfl/social-nce}{https://github.com/vita-epfl/social-nce}}. We attempted to verify the results claimed by the authors and reimplemented their code in PyTorch Lightning.