Discusses advanced reinforcement learning techniques, focusing on deep and robust methods, including actor-critic frameworks and adversarial learning strategies.
Covers the basics of reinforcement learning, including Markov Decision Processes and policy gradient methods, and explores real-world applications and recent advances.
Explores bug-finding, verification, and the use of learning-aided approaches in program reasoning, showcasing examples like the Heartbleed bug and differential Bayesian reasoning.
Covers model-free prediction methods in reinforcement learning, focusing on Monte Carlo and Temporal Differences for estimating value functions without transition dynamics knowledge.
Explores the evolution of CNNs in image processing, covering classical and deep neural networks, training algorithms, backpropagation, non-linear steps, loss functions, and software frameworks.