Reinforcement Learning - Pac-Man
Explore reinforcement learning through building a Pac-Man-beating agent. Gain insights into Q-learning, deep Q-learning with neural networks, and practical implementation using libraries like Keras.
Introduction to Reinforcement Learning Theory and Methods - Lecture 1
Master the fundamentals of reinforcement learning through theoretical concepts and practical applications, covering Markov decision processes, dynamic programming, and temporal differences with hands-on exercises.
A Short Course on Reinforcement Learning - Lecture 2
Master the fundamentals of reinforcement learning through comprehensive lectures covering Markov decision processes, dynamic programming, and temporal differences, with hands-on practical applications.
Robot Learning with Inspiration from Child Development
Explore cutting-edge developments in robot learning across locomotion, navigation, and manipulation, drawing parallels from child development to advance intelligent robotics through simulation and real-world applications.
Uncertainty Quantification with Conformal Prediction - A Path to Reliable ML Models
Dive into conformal prediction techniques for quantifying uncertainty in ML models, covering implementation across various domains and practical applications using Python and pre-trained neural networks.
Improved Assistance for Interactive Proof - Machine Learning in Theorem Proving
Explore machine learning techniques enhancing interactive theorem provers, from established methods to emerging challenges in automation and efficient interaction.
Practical Reinforcement Learning with Robots
Explore practical reinforcement learning for robotics, covering environment design in simulation and real-world applications, with insights on implementing RL in robotic systems.
Advanced Techniques for Online Advertisement Spend Optimization
Explore advanced techniques for optimizing online ad spend using Reinforcement Learning, Bayesian statistics, and Thompson sampling to improve budget allocation and maximize returns.
Decision Awareness in Reinforcement Learning
Explore decision awareness in reinforcement learning, focusing on control-oriented transition models and neural ODEs for nonlinear trajectory optimization. Discuss computational challenges and scaling solutions.
Learning to Bound Using Decision Diagrams and Reinforcement Learning
Explore decision diagrams and reinforcement learning for tighter bounds in discrete optimization, enhancing branch-and-bound algorithms with improved variable ordering techniques.
How to Use Mean-Field Control for Restless Bandits and Weakly Coupled MDPs
Explore mean-field control techniques for resource allocation in weakly coupled MDPs and restless bandits, focusing on LP-based relaxations and asymptotic optimality.
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
Explore a novel fine-tuning method for Large Language Models that improves performance without additional human-annotated data, using self-play mechanisms and theoretical guarantees.
Neural Architecture Search - Part I
Explore neural architecture search techniques, focusing on automated design of efficient deep learning models for various applications.
Neural Architecture Search - Part I (EfficientML.ai) - Lecture 7
Explore neural architecture search techniques for optimizing deep learning models, covering fundamentals, methods, and applications in AI efficiency.
Neural Architecture Search - Part II - Lecture 8
Explore advanced neural architecture search techniques, including gradient-based methods and hardware-aware NAS, to optimize deep learning models for efficiency and performance.
Neural Architecture Search (Part II) - Lecture 8
Explore advanced neural architecture search techniques, including evolutionary algorithms and reinforcement learning, to optimize deep learning models for efficiency and performance.
Neural Architecture Search Part I - Lecture 7
Explore neural architecture search techniques for optimizing deep learning models, covering fundamental concepts and cutting-edge approaches in AI efficiency.
Neural Architecture Search Part I - Lecture 7
Explore neural architecture search techniques for optimizing deep learning models, focusing on automated design and efficiency in AI systems.
Neural Architecture Search Part II - Lecture 8
Explore advanced neural architecture search techniques, including evolutionary algorithms and reinforcement learning, to optimize deep learning models for efficiency and performance.
Neural Architecture Search Part II - Lecture 8
Explore advanced neural architecture search techniques, including evolutionary algorithms and reinforcement learning for optimizing deep learning models.
Adversarial Machine Learning: Beyond Manipulating Pixels and Words
Explore vulnerabilities in sequential machine learning and challenge assumptions about imperceptible attacks on image classification through human behavioral studies.