The emergence of large language model (LLM)-based agents has significantly advanced the development of autonomous machine learning (ML) engineering. However, most existing approaches rely heavily on manual prompt engineering, failing to adapt and optimize based on diverse experimental experiences. Focusing on this, for the first time, we explore the paradigm of learning-based agentic ML, where an LLM agent learns through interactive experimentation on ML tasks using online reinforcement learning (RL). To realize this, we propose a novel agentic ML training framework with three key components: (1) exploration-enriched fine-tuning, which enables LLM agents to generate diverse actions for enhanced RL exploration; (2) step-wise RL, which enables training on a single action step, accelerating experience collection and improving training efficiency; (3) an agentic ML-specific reward module, which unifies varied ML feedback signals into consistent rewards for RL optimization. Leveraging this framework, we train ML-Agent, driven by a 7B-sized Qwen-2.5 LLM for autonomous ML. Remarkably, despite being trained on merely 9 ML tasks, our 7B-sized ML-Agent outperforms the 671B-sized DeepSeek-R1 agent. Furthermore, it achieves continuous performance improvements and demonstrates exceptional cross-task generalization capabilities.

Recent advancements in large language models (LLMs) have enabled their use as agents for planning complex tasks. Existing methods typically rely on a thought-action-observation (TAO) process to enhance LLM performance, but these approaches are often constrained by the LLMs' limited knowledge of complex tasks. Retrieval-augmented generation (RAG) offers new opportunities by leveraging external databases to ground generation in retrieved information. In this paper, we identify two key challenges (enlargability and transferability) in applying RAG to task planning. We propose InstructRAG, a novel solution within a multi-agent meta-reinforcement learning framework, to address these challenges. InstructRAG includes a graph to organize past instruction paths (sequences of correct actions), an RL-Agent with Reinforcement Learning to expand graph coverage for enlargability, and an ML-Agent with Meta-Learning to improve task generalization for transferability. The two agents are trained end-to-end to optimize overall planning performance. Our experiments on four widely used task planning datasets demonstrate that InstructRAG significantly enhances performance and adapts efficiently to new tasks, achieving up to a 19.2% improvement over the best existing approach.

Network Slicing (NS) has transformed the landscape of resource sharing in networks, offering flexibility to support services and applications with highly variable requirements in areas such as the next-generation 5G/6G mobile networks (NGMN), vehicular networks, industrial Internet of Things (IoT), and verticals. Although significant research and experimentation have driven the development of network slicing, existing architectures often fall short in intrinsic architectural intelligent security capabilities. This paper proposes an architecture-intelligent security mechanism to improve the NS solutions. We idealized a security-native architecture that deploys intelligent microservices as federated agents based on machine learning, providing intra-slice and architectural operation security for the Slicing Future Internet Infrastructures (SFI2) reference architecture. It is noteworthy that federated learning approaches match the highly distributed modern microservice-based architectures, thus providing a unifying and scalable design choice for NS platforms addressing both service and security. Using ML-Agents and Security Agents, our approach identified Distributed Denial-of-Service (DDoS) and intrusion attacks within the slice using generic and non-intrusive telemetry records, achieving an average accuracy of approximately $95.60\%$ in the network slicing architecture and $99.99\%$ for the deployed slice -- intra-slice. This result demonstrates the potential for leveraging architectural operational security and introduces a promising new research direction for network slicing architectures.

Setup and explore the Unity ML-Agents plugin. Setup and use Tensorflow to train game characters. Apply newfound knowledge of machine learning to integrate contemporary research ideas in the field into their own projects. Use a Proximal Policy Optimisation to train a neural network. Setup and explore the Unity ML-Agents plugin.

What if you could build a character that could learn while it played? Think about the types of gameplay you could develop where the enemies started to outsmart the player. This is what machine learning in games is all about. In this course, we will discover the fascinating world of artificial intelligence beyond the simple stuff and examine the increasingly popular domain of machines that learn to think for themselves. In this course, Penny introduces the popular machine learning techniques of genetic algorithms and neural networks using her internationally acclaimed teaching style and knowledge from a Ph.D in game character AI and over 25 years experience working with games and computer graphics.

What if you could build a character that could learn while it played? Think about the types of gameplay you could develop where the enemies started to outsmart the player. This is what machine learning in games is all about. In this course, we will discover the fascinating world of artificial intelligence beyond the simple stuff and examine the increasingly popular domain of machines that learn to think for themselves. In this course, Penny introduces the popular machine learning techniques of genetic algorithms and neural networks using her internationally acclaimed teaching style and knowledge from a Ph.D in game character AI and over 25 years experience working with games and computer graphics.

Unity 3D is a popular platform for creating and operating interactive, real-time 3D content. It is a cross-platform 3D engine and a user-friendly integrated development environment (IDE) which helps in creating games in 3D as well as applications for desktop, mobile, web and more. It consists of a number of tools for programmers as well as artists to create real-time solutions, such as films and automotive, apart from games. With a vision to maximise the transformative impact of Machine Learning for researchers and developers, Unity released the first version of Unity Machine Learning Agents Toolkit (ML-Agents) in 2017. The aim of this ML environment is to allow game developers and AI researchers to use Unity as a platform to train as well as embed intelligent agents with the help of the latest advancements in ML and AI.

We often hear in the news about this thing called "machine learning" and how computers are "learning" to perform certain tasks. From the examples we see, it almost seems like magic when a computer creates perfect landscapes from thin air or makes a painting talk. But what is often overlooked, and what we want to cover in this tutorial, is that machine learning can be used in video game creation as well. In other words, we can use machine learning to make better and more interesting video games by training our AIs to perform certain tasks automatically with machine learning algorithms. This tutorial will show you how we can use Unity ML agents to make an AI target and find a game object. More specifically, we'll be looking at how to customize the training process to create an AI with a very specific proficiency in this task. Through this, you will get to see just how much potential machine learning has when it comes to making AI for video games. So, without further ado, let's get started and learn how to code powerful AIs with the power of Unity and machine learning combined!

In this Machine Learning tutorial, we'll build a video game with Unity, TensorFlow and Python. We'll show you how easy it is to add ML-powered intelligence to video games or simulations, and how inference on smartphones is easier than it's ever been: modern, powerful tools like Unity's ML-Agents, Python, and TensorFlow make the complex easy. In this session, we'll build a little smartphone game, train a bot to play it using reinforcement learning, Python, and TensorFlow, and deploy it to a smartphone. We'll show you how easy it is to add ML-powered intelligence to video games or simulations, and how inference on smartphones is easier than it's ever been: modern, powerful tools like Unity's ML-Agents, Python, and TensorFlow make the complex easy. First, we'll spend 10 minutes of the session: Second, we'll spend 10 minutes of the session: Finally, we'll spend the last 10 minutes of the session: This is an engaging, fast-paced, and surprisingly in-depth exploration of how powerful modern game engines can be used for quick, relatively easy, but incredibly powerful state of the art machine learning and training, and how powerful inference on-device is, for mobile AI.

The past few years have witnessed breakthroughs in reinforcement learning (RL). From the first successful use of RL by a deep learning model for learning a policy from pixel input in 2013 to the OpenAI Dexterity program in 2019, we live in an exciting moment in RL research. Consequently, we need, as RL researchers, to create more and more complex environments and Unity helps us to do that. Unity ML-Agents toolkit is a new plugin based on the game engine Unity that allows us to use the Unity Game Engine as an environment builder to train agents. From playing football, learning to walk, to jump big walls, to train a cute doggy to catch sticks, Unity ML-Agents Toolkit provides a ton of amazing pre-made environment.