Yannic Kilcher Courses

Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discovery

Explore dynamical distance learning for reinforcement agents, enhancing policy learning through state distance estimation. Discover applications in semi-supervised and unsupervised skill acquisition.

• YouTube
• 23 minutes
• Self-Paced
• Free Video

CURL - Contrastive Unsupervised Representations for Reinforcement Learning

Explore how contrastive learning enhances reinforcement learning, improving performance in complex tasks using high-level features extracted from raw pixels.

• YouTube
• 29 minutes
• Self-Paced
• Free Video

Evolving Normalization-Activation Layers

Explore evolutionary search for optimal normalization-activation layers in neural networks, uncovering novel designs that outperform traditional methods across various image-related tasks.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

POET - Endlessly Generating Increasingly Complex and Diverse Learning Environments and Solutions

Explore POET, an innovative algorithm that generates and solves increasingly complex challenges, fostering open-ended learning and diverse problem-solving capabilities through evolutionary methods and transfer learning.

• YouTube
• 34 minutes
• Self-Paced
• Free Video

Dream to Control - Learning Behaviors by Latent Imagination

Explore DeepMind's Dreamer, an innovative RL agent that learns complex behaviors through latent imagination, surpassing existing approaches in visual control tasks.

• YouTube
• 23 minutes
• Self-Paced
• Free Video

Agent57 - Outperforming the Atari Human Benchmark

Explore DeepMind's Agent57, the first AI to surpass human performance in all 57 Atari games. Learn about its innovative approach to reinforcement learning and meta-learning for exploration-exploitation balance.

• YouTube
• 32 minutes
• Self-Paced
• Free Video

Axial Attention & MetNet - A Neural Weather Model for Precipitation Forecasting

Explore a neural network model for precise precipitation forecasting using axial attention, offering high-resolution predictions up to 8 hours ahead with improved accuracy over traditional methods.

• YouTube
• 33 minutes
• Self-Paced
• Free Video

Deep Learning for Symbolic Mathematics

Explore neural networks solving complex mathematical problems like symbolic integration and differential equations, outperforming traditional Computer Algebra Systems.

• YouTube
• 24 minutes
• Self-Paced
• Free Video

Turing-NLG, DeepSpeed and the ZeRO Optimizer

Explore Microsoft's 17-billion parameter language model, ZeRO optimizer, and DeepSpeed, enabling efficient model and data parallelism for state-of-the-art natural language processing breakthroughs.

• YouTube
• 21 minutes
• Self-Paced
• Free Video

Interview - Mark Ledwich - Algorithmic Extremism: Examining YouTube's Rabbit Hole of Radicalization

Exploring YouTube's recommendation algorithm and its impact on political content consumption, debunking claims of radicalization and revealing preferences for mainstream media.

• YouTube
• 26 minutes
• Self-Paced
• Free Video

Reformer - The Efficient Transformer

Discover how Reformer revolutionizes Transformer models, reducing memory usage and enabling processing of longer sequences through innovative techniques like Locality Sensitive Hashing and Reversible Networks.

• YouTube
• 29 minutes
• Self-Paced
• Free Video

Reinforcement Learning Upside Down - Don't Predict Rewards, Just Map Them to Actions

Innovative approach to reinforcement learning that maps desired rewards to actions, transforming it into supervised learning. Shows promising performance compared to traditional RL algorithms.

• YouTube
• 27 minutes
• Self-Paced
• Free Video

A Neurally Plausible Model Learns Successor Representations in Partially Observable Environments

Explores a neurally plausible model using distributional successor features for efficient reinforcement learning in partially observable, noisy environments, bridging model-based and model-free approaches.

• YouTube
• 37 minutes
• Self-Paced
• Free Video

AlphaStar - Grandmaster Level in StarCraft II Using Multi-Agent Reinforcement Learning

Explore DeepMind's AI agent achieving Grandmaster-level skill in StarCraft II through innovative multi-agent reinforcement learning and League Training techniques.

• YouTube
• 37 minutes
• Self-Paced
• Free Video

IMPALA - Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

Explore IMPALA, a distributed reinforcement learning architecture for efficient multi-task learning. Learn about V-trace, off-policy correction, and scalable performance across thousands of machines.

• YouTube
• 21 minutes
• Self-Paced
• Free Video