Nonconvex Homogenization for 1D Controlled Brownian Motion in a Random Potential
Explores stochastic control of Brownian motion in random potentials, analyzing optimal payoff growth and Bellman equation homogenization. Discusses effective Hamiltonians and distinct control regimes.
The Role of Conventions in Adaptive Human-AI Interaction
Explores partner modeling in multi-agent coordination, focusing on representation learning, conventions, and strategies for reducing non-stationarity in decentralized systems.
Fast Reinforcement Learning With Generalized Policy Updates
Explore advanced techniques in deep reinforcement learning, focusing on generalized policy updates for rapid learning and improved performance in complex environments.
Attacking the Off-Policy Problem With Duality
Explore deep reinforcement learning techniques to address off-policy challenges using duality principles, enhancing AI decision-making in complex environments.
Every Optimization Problem Is a Quadratic Program
Explore how diverse optimization problems can be reframed as quadratic programs, offering insights into reinforcement learning theory and practical applications.
How EleutherAI Trains and Releases LLMs - Interview with Stella Biderman
Explore EleutherAI's approach to LLM development, covering model selection, training techniques, GPU choices, and interpretability challenges in this insightful interview with Stella Biderman.
Learning to Optimize High Dimensional Optimization Problems
Explore deep neural networks and reinforcement learning for solving high-dimensional optimization problems, improving performance in job scheduling, neural architecture search, and black-box optimization.
Productionizing Deep Reinforcement Learning with Spark and MLflow
Aprenda a aplicar Deep Reinforcement Learning em escala usando Spark e MLflow para personalização de jogos e aumento de engajamento, com dicas práticas para superar desafios de produção.
Introduction to Q-Learning for Game Play - Lecture 12.2
Explore Q-Learning for game AI: build policy tables, suggest optimal actions, and apply Python techniques for environment-based decision-making in this introduction.
2019 ADSI Summer Workshop- Algorithmic Foundations of Learning and Control
Explore uncertainty in perception for control systems, covering model-free algorithms, pixel-based control, and machine learning applications in robotics and autonomous systems.
2019 ADSI Summer Workshop- Algorithmic Foundations of Learning and Control
Explore advanced techniques in reinforcement learning, focusing on randomized value functions and their applications in exploration strategies for complex decision-making problems.
ADSI Summer Workshop: Algorithmic Foundations of Learning and Control - Emma Brunskill
Explore batch/counterfactual reinforcement learning techniques to optimize decision-making with minimal data, focusing on policy evaluation, generalization bounds, and applications in healthcare simulations.
ADSI Summer Workshop- Algorithmic Foundations of Learning and Control
Explore model-based control for physical systems, covering inverse dynamics, optimization techniques, and automated discovery methods for advanced robotics and control applications.
ADSI Summer Workshop- Algorithmic Foundations of Learning and Control
Explore stable and efficient reinforcement learning algorithms with Csaba Szepesvári's presentation on Politex, focusing on generalization and pseudo regret in online learning and linear prediction.
Reinforcement Learning - Emma Brunskill - Stanford University
Explore reinforcement learning fundamentals, applications, and challenges with Stanford's Emma Brunskill, covering AI planning, machine learning, and decision-making processes.
Bandits - Kevin Jamieson - University of Washington
Explore bandit algorithms and their applications in machine learning, from drug development to content recommendation, with a focus on regret minimization and stochastic models.
Natural Language Processing - Yoav Artzi - Cornell University
Explore natural language instruction following for robots and collaborative scenarios, featuring new datasets, interpretable models, and learning methods combining supervised and reinforcement approaches.
Decision-Theoretic Planning to Control Crowdsourced Workflows
Explores decision-theoretic planning for optimizing crowdsourced workflows, covering POMDPs, dynamic workflow switching, taxonomy construction, and data annotation optimization for machine learning applications.
tinyMAN - Lightweight Energy Manager Using Reinforcement Learning for Energy Harvesting Wearable IoT Devices
Explore reinforcement learning for energy management in IoT wearables, focusing on tinyMAN's lightweight approach to achieve energy-neutral operation in harvesting devices.
Learning Robust Driving Policies
Explore robust driving policies for autonomous vehicles, covering situational reasoning strategies and addressing covariate shift in imitation learning to improve generalization and safety in diverse conditions.
RL Foundation Models Are Coming!
Explore DeepMind's AdA algorithm, combining meta-learning, attention, and curriculum learning for advanced reinforcement learning. Discover promising results and future prospects in this emerging field.