Fast Learning of Small Strategies - Jan Křetínský, Technical University of Munich
Discover fast learning techniques for small strategies in Markov decision processes, combining verification precision with machine learning scalability for ε-optimal strategies and concise representation.
Risk-Aware Reinforcement Learning for Finance
Explore risk-aware reinforcement learning in finance, covering time-consistent approaches and applications to financial modeling. Learn from expert Sebastian Jaimungal about innovative strategies beyond traditional RL methods.
Optimizing Wireless Cellular Networks with Reinforcement Learning: Technology Deep Dive, Lessons Learned and Field Results
Explore reinforcement learning techniques for optimizing wireless networks, including deep dives, lessons learned, and real-world field results from Ericsson experts.
Machine Learning in Biology - Teaching a Glider to Soar Like a Bird
Explore machine learning's role in enhancing autonomous glider performance, inspired by bird soaring techniques and atmospheric dynamics.
Theoretical Foundations of Reinforcement Learning
Explore key concepts and mathematical principles underlying reinforcement learning algorithms, including Markov decision processes, value functions, and policy optimization techniques.
Building the Best RLHF Library - TRLX Development with Louis Castricato
Explore the journey of building CarperAI and the TRLX library for RLHF, featuring insights on open-source development and the growth of AI projects.
Teaching ChatGPT a New Programming Language - Creating a Custom GPT for Keel
Learn to create a custom GPT-4 agent for Keel schema language, explore AI programming, and dive into web development with WebAssembly, TypeScript, and React. Gain insights on AI's potential in software engineering.
Hyperparameter Optimization for Reinforcement Learning Using Meta's Ax
Learn to optimize hyperparameters for reinforcement learning using Meta's Ax framework. Explore grid search, random search, and Bayesian optimization techniques to improve machine learning model performance.
ChatGPT: From Zero to Hero - Understanding the Technology and Training Process
Comprehensive exploration of ChatGPT's architecture, from fundamental concepts to advanced fine-tuning techniques, covering GPT models, reward systems, and reinforcement learning applications.
Q-Learning: From Basics to Deep Q-Networks
Explore Q-Learning fundamentals, from Markov Decision Processes to Deep Q-Networks, in this comprehensive overview of reinforcement learning concepts and applications.
TinyRL: Teaching AI to Swing Up a Real Pendulum
Explore reinforcement learning to train an AI agent to swing up a real pendulum using Arduino, Python frameworks, and ESP32 deployment, with practical demonstrations and troubleshooting tips.
Deep Q-Network Image Processing and Environment Management - Reinforcement Learning Code Project
Learn to manage environments and process images for deep Q-networks in reinforcement learning, focusing on the cart and pole problem implementation.
Language and Video-Generative AI in Autonomous Driving - Guest Lecture by Wayve
Explore Wayve's innovative approach to autonomous driving, featuring language and video-generative AI advancements. Learn about GAIA-1 and LINGO technologies, and their applications in self-driving vehicles.
Reinforcement Learning From Small Data in Feature Space - 2019 ADSI Summer Workshop
Explore reinforcement learning in feature space with small datasets, focusing on innovative approaches and algorithmic foundations presented by Princeton researcher Mengdi Wang.
Sample-Efficient Exploration in Reinforcement Learning with Rich Observations - 2019
Explore sample-efficient reinforcement learning with rich observations in this insightful presentation by Microsoft Research's Alekh Agarwal at the ADSI Summer Workshop.
Reinforcement Learning - Lecture 5
Explore advanced reinforcement learning concepts with Stanford's Emma Brunskill, covering cutting-edge techniques and applications in AI decision-making.
Reinforcement Learning IV - Advanced Concepts and Applications
Explore advanced reinforcement learning concepts with Stanford's Emma Brunskill, covering cutting-edge techniques and applications in AI decision-making.
Reinforcement Learning III - Advanced Concepts and Applications
Explore advanced reinforcement learning concepts with Stanford's Emma Brunskill, covering cutting-edge techniques and applications in AI decision-making.
Reinforcement Learning II - Advanced Concepts and Applications
Explore advanced reinforcement learning concepts with Stanford's Emma Brunskill, covering cutting-edge techniques and applications in AI decision-making.
Bandits IV - Advanced Techniques in Multi-Armed Bandit Algorithms
Explore advanced bandit algorithms and their applications in machine learning with Kevin Jamieson from the University of Washington.
Enhanced POET - Open-ended Reinforcement Learning through Unbounded Invention of Learning Challenges
Explore open-ended reinforcement learning through unbounded invention of challenges and solutions, focusing on Uber's Enhanced POET algorithm and its applications in AI development.