A Path Towards Autonomous Machine Intelligence
Explore Yann LeCun's vision for autonomous machine intelligence, delving into cutting-edge AI concepts and potential future developments in the field.
Functional and Structural Connectome of Reinforcement Learning
Explore functional and structural connectomes of reinforcement learning, focusing on neural substrates, computational models, and applications in depression research.
Quantum Error Correction of Bosonic Qudits Beyond Break-even
Explore quantum error correction for qudits, focusing on experimental demonstrations of error-corrected logical qutrits and ququarts using the GKP bosonic code in circuit QED architecture.
Hierarchical Imitation Learning with Vector Quantized Models
Learn hierarchical imitation learning techniques using vector quantized models for complex decision-making tasks, exploring subgoal identification and planning strategies to outperform expert demonstrations.
Scalable and Flexible Distributed Reinforcement Learning Systems
Explore scalable distributed reinforcement learning systems, focusing on flexible training loops, statement management, and GPU allocation. Gain insights into building efficient RLHF systems for large-scale applications.
Planning with Diffusion for Flexible Behavior Synthesis
Learn flexible behavior synthesis using diffusion models for planning, exploring compositional trajectories, goal-directed planning, and offline reinforcement learning techniques.
Faster Saddle-Point Optimization for Solving Large-Scale Markov Decision Processes
Explore advanced techniques for optimizing large-scale Markov decision processes using saddle-point methods. Gain insights into theoretical reinforcement learning and linear programming formulations.
Adversarially Robust Stochastic Multi-Armed Bandits
Explore adversarially robust stochastic multi-armed bandits for optimal experimental design. Learn about algorithms balancing fast and robust learning in real-world applications like digital advertising.
Modelling and Controlling Turbulent Flows through Deep Learning
Explore deep learning applications in modeling and controlling turbulent flows, from flow reconstruction to reinforcement learning for flow control, with insights on CNN architectures and transfer learning.
AI for Cyber Defence
Explore AI applications in cybersecurity with PhD candidates discussing reinforcement learning solutions and the potential for automation in addressing cyber challenges.
Temporal Difference Learning for Model Predictive Control - Research Presentation 3
Presentation on Temporal Difference Learning for Model Predictive Control, exploring innovative approaches in robotics and AI. Insights into recent papers and project developments by researcher Nicklas Hansen.
Specification-guided Reinforcement Learning
Explore specification-guided reinforcement learning techniques for synthesizing models and systems, presented by Rajeev Alur from the University of Pennsylvania.
Data-Driven Fine Manipulation in Robotics - 2024 Winter Robotics Colloquium
Data-driven approaches for fine manipulation in robotics, enhancing precision and adaptability. Research focuses on empowering general-purpose hardware systems to automate delicate tasks using imitation learning and reinforcement learning techniques.
Online Learning and Bandits - Part 1
Explore online learning and bandit algorithms with experts from DeepMind and CWI. Gain insights into gradient descent, exponential weights, and regularized leader methods for reinforcement learning.
Hello AI World! - Why Developers Should Care About AI
Explore modern AI tools for developers, including machine learning and deep learning, to enhance products and services. Learn to leverage AI capabilities through simple API calls.
Reinforcement Learning with TorchRL and TensoDict - NeurIPS Hacker Cup AI
Explore TorchRL and TensoDict for advanced reinforcement learning in PyTorch, covering RLHF, data handling, and practical applications for streamlined RL workflows.
Reinforcement Learning and Architectures of Intelligence - Part 1
Explore reinforcement learning and intelligence architectures with Microsoft Research's Ida Momennejad in this comprehensive tutorial from IPAM's Mathematics of Intelligences series.
Towards Long-Horizon Robot Task Learning
Explore cutting-edge research on complex robot task learning, including simulation environments, hierarchical decomposition, and skill chaining for long-horizon tasks in robotics and AI.
Reinforcement Learning Optimization of Charging a Dicke Quantum Battery
Explore reinforcement learning optimization for Dicke quantum batteries, enhancing energy extraction and charging precision beyond standard methods.
Using Unity's Machine Learning Agents on Arm for Game Character Training
Explore Unity's ML-Agents for intelligent game characters on Arm devices. Train agents using reinforcement learning for single and multi-agent scenarios in games and apps.
Knowing the What But Not the Where in Bayesian Optimization
Explore Bayesian optimization techniques for finding optimal inputs when outputs are known. Enhance efficiency in hyperparameter tuning for deep reinforcement and supervised learning.