Inside TensorFlow - TF-Agents
Explore TF-Agents, TensorFlow's reinforcement learning library, with experts demonstrating its capabilities, architecture, and applications in game playing, bandits, and recommender systems.
Building a Level 5 Autonomous Vehicle in TrackMania
Explore the development of a self-driving car in TrackMania using reinforcement learning. Learn about the AI pipeline, from feature selection to model training, and witness the impressive results in action.
Towards Trustworthy Automatic Diagnosis Systems by Emulating Doctors' Reasoning with Deep Reinforcement Learning
Explore deep reinforcement learning for automated medical diagnosis, emulating doctors' reasoning to generate differential diagnoses, prioritize severe pathologies, and enhance system trustworthiness.
Using Reinforcement Learning in Large Scale Automation at Netflix
Optimize automation schedules and reduce failure detection time using self-service reinforcement learning tools. Learn from Netflix's applied RL service deployment experience.
Tracing the Path to Self-adapting AI Agents
Discover how Trace, a groundbreaking AutoDiff-like framework, enables end-to-end training of AI workflows using general feedback, revolutionizing how AI agents learn and adapt through Python-based implementation.
Optimizing Recommendations on Wattpad Home - Building a Multi-Objective Recommender System
Discover how Wattpad optimizes its recommendation system using reinforcement learning and graph neural networks to enhance user engagement and solve content discovery challenges.
Write Your Own AI Agent with Monte Carlo Tree Search - Building a Tic-Tac-Toe Game
Master Monte Carlo Tree Search algorithm implementation by building a Tic-Tac-Toe AI agent, exploring its applications in modern AI systems like AlphaGo and O1 models.
Direct Preference Optimization (DPO) vs RLHF - Understanding Language Model Training
Delve into Direct Preference Optimization (DPO) and discover how it eliminates the need for separate reward models in language model training, offering a more efficient alternative to RLHF.
Real-World AI: Risk and Robustness in Reinforcement Learning and Kalman Filtering
Explore real-world applications of AI through risk-aware reinforcement learning and robust Kalman filtering, focusing on practical challenges and solutions for handling uncertainties in AI systems.
Missing Mass and Optimal Discovery in Power Systems Security Analysis
Explore advanced statistical modeling and machine learning concepts through probabilistic expert advice, focusing on security analysis in power systems and Good-Turing missing mass estimation techniques.
Markov Chain Variance Estimation - A Stochastic Approximation Approach
Delve into advanced statistical methods for Markov chain variance estimation, exploring stochastic approximation techniques and their applications in reinforcement learning and sequential decision-making.
인공지능 기반 펀드 운용 시스템: AI-Advisor의 개발과 적용
Discover how SK's AI-powered robo-advisor revolutionizes fund management through deep learning and reinforcement learning, offering innovative solutions for financial investment products and market strategies.
Generative AI and Large Language Models: From GPT-3 to ChatGPT with RLHF
Explore the latest advancements in generative AI, from CodeWhisperer to ChatGPT, while learning about prompt engineering and reinforcement learning techniques for improved human-AI interaction.
Multi-Agent AI Systems: From Imitation Learning to Markov Game Theory
Explore advanced game theory concepts in multi-agent AI systems, covering investment strategies, cybersecurity applications, and the evolution from reinforcement learning to imitation learning frameworks.
Beyond Rules and Rewards: From Pixels to Adaptive Policies Through Imitation, Reinforcement, and Multimodal Learning
Explore advanced robotic learning methodologies, from imitation-based training to multimodal systems, focusing on adaptive policies and vision-language models for enhanced real-world robot interactions.
Haskell for Choice-Based Learning in Machine Learning Programming
Explore language design for machine learning, focusing on choice-based learning. Combine algebraic effects, handlers, and selection monad to create powerful frameworks for decision-making models and optimization techniques.
Ubisoft La Forge Game Bot Team - Building ML-Based Game Actors
Explore Ubisoft La Forge's ML-based game actors, challenges in AAA games, and innovative approaches to simulating player behavior through concrete in-game examples.
Introduction to Reinforcement Learning - Creating AI for Atari Games
Explore reinforcement learning and convolutional neural networks to create AI for Atari games. Gain practical code examples and navigate deep reinforcement learning complexities.
Maximizing Engagement Through Privacy-Preserving Content Recommendations
Explore innovative approaches to recommendation systems that maximize engagement while preserving user privacy, using reinforcement learning and semantic analysis techniques.
Sustaining Git Performance Under Heavy Workloads - AI-driven Approach
Explore AI-driven strategies for maintaining Git repository performance under heavy workloads, including partial repacking and bitmap regeneration techniques.
Reinforcement Learning for Non-Markovian Environments
Explore key issues in reinforcement learning for non-Markovian environments, drawing parallels with stochastic control and discussing approximation of conditional laws.