The Famous Batteries and Flashlight Logic Puzzle - Optimal Testing Strategy
Solve a famous logic puzzle: determine the minimum tests needed to find 2 good batteries out of 4 good and 4 bad ones to power a flashlight. Explores strategies and provides proof.
Expected Value - The $10 Bet (Part 1 of 2)
Explore the concept of expected value through a $10 bet scenario, gaining insights into probability and decision-making in uncertain situations.
Statistical Contract Theory
Explore statistical contract theory with Michael Jordan, delving into mathematical, economic, and computational aspects of matchings and markets.
Foundations of Neo-Bayesian Statistics - Part 2
Explore Neo-Bayesian Statistics foundations, examining alternative probability theories and their implications for statistical inference, dynamic consistency, and capacity updating.
Decision Making and Learning in the Life Sciences - Lecture 2
Explore decision-making and learning in life sciences, focusing on advanced concepts and their applications in biological systems and research.
Chance and Necessity: Decision Making in Single Cancer Cells - Lecture 2
Explore decision-making processes in individual cancer cells, examining the interplay between randomness and determinism in cellular behavior and its implications for cancer progression.
Multi-Agent Dynamics with Self-Play Reinforcement Learning
Explore how self-play techniques in multi-agent reinforcement learning revolutionize game theory, enabling AI agents to develop advanced strategies through autonomous learning and competition.
Risk-Sensitive Bandits - Arm Mixtures Optimality and Regret-Efficient Algorithms
Delve into risk-aware sequential decision-making through distortion riskmetrics, exploring optimal arm mixture strategies and new algorithms for tracking these mixtures in multi-armed bandit problems.
Almost-Optimal Best Restless Markov Arm Identification with Fixed Confidence
Delve into advanced multi-armed bandit theory, focusing on identifying optimal arms in restless Markov chains through asymptotic analysis and policy optimization for distributed learning systems.
A Smoothed Analysis of the Greedy Algorithm for Linear Contextual Bandits - Theory Seminar
Explore smoothed analysis of greedy algorithms in bandit learning, addressing fairness concerns in decision-making while achieving "no regret" performance in slightly perturbed environments.
Advances in Risk-Aware Multi-Armed Bandit Problems - Lecture 3
Explore risk-aware multi-armed bandit problems with Vincent Tan. Learn advanced techniques for balancing exploration and exploitation in uncertain decision-making scenarios.
Markov Decision Processes
Explore Markov Decision Processes, their components, and applications in inventory management. Learn about rewards, discounting, and Bellman's equation for optimal decision-making.
Pandora's Box with Correlations - Learning and Approximation
Explore learning and approximation techniques for correlated Pandora's Box problems, focusing on algorithmic approaches and theoretical insights.
Scaling Decision-Theoretic Probabilistic Programming Through Factorization
Explore dappl, a new probabilistic programming language for decision-making, offering scalable MEU reasoning and expressive modeling of complex real-world tasks.
Information and Decision Theory Explain Neural Pulse Trains - Lecture
Explore information and decision theory's application to neural communication, uncovering insights into pulse trains and channel capacity in the peripheral nervous system.
Wizards of Odds - The Power of Probability
Experts explore probability's subtle nature and its crucial role in science, technology, medicine, and daily life, offering insights into common misconceptions and its powerful applications.
Multi-Modal, Pre-Trained Models in Verifiable Sequential Decision-Making - Metacognitive AI
Explore multi-modal, pre-trained models in verifiable sequential decision-making for metacognitive AI, focusing on latest advancements and applications in artificial intelligence.
Strategic, Tactical and Operational Decision Making
Explore strategic, tactical, and operational decision-making processes to enhance organizational effectiveness and achieve long-term goals.
Nonconvex Stochastic Programs: Chance Constraints
Explore nonconvex stochastic programs and chance constraints with Jong-Shi Pang, delving into advanced mathematical concepts for optimization under uncertainty.
Min LQG Games and Collective Discrete Choice Problems in Decision Making
Explore linear quadratic Gaussian games and their applications in social choice dynamics, election patterns, and micro-robotic exploration through mathematical modeling and Nash equilibria analysis.
Unsupervised Environment Design
Explore automatic generation of environments for training RL agents, from GenIE to Unsupervised Environment Design, bridging classical decision theory and deep learning.