Implementation of tensor-based dynamic mode decomposition algorithm using JAX

Reinforcement Learning: From Bandits to LLM Alignment — Open textbook with 17 chapters, Colab notebooks, and exercises

Interactive platform for exploring and visualizing reinforcement learning algorithms — from tabular methods to deep RL and RLHF. Compare methods, tune hyperparameters, and analyze training dynamics…

This repository contains lecture notes, practical materials, and implementations for the course: "Reinforcement Learning: from Bandits to RLHF" The course is designed to provide a deep and systemat…

Unofficial PyTorch Implementation of "Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential".

This repository contains the Hugging Face Agents Course.

Config files for my GitHub profile.

Репозиторий с материалами курса, читаемого Пчелиным Константином весной 2025 года в МГУ