Egor Cherepanov's starred repositories
Practical_RL
A course in reinforcement learning in the wild
MAPF-GPT
This repository contains MAPF-GPT, a deep learning-based model for solving MAPF problems. Trained with imitation learning on trajectories produced by LaCAM, it generates collision-free paths under partial observability without heuristics or agent communication. MAPF-GPT excels on unseen instances and outperforms state-of-the-art solvers.
Transformer-from-scratch
I will build Transformer from scratch
reinforcement_learning_course
The page of the Ural Federal University course "Reinforcement Learning and Neural Networks"
reinforcement-learning
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
generative-ai-for-beginners
18 Lessons, Get Started Building with Generative AI đź”— https://microsoft.github.io/generative-ai-for-beginners/
endless-memory-gym
Challenging Memory-based Deep Reinforcement Learning Agents
dreamerv3-torch
Implementation of Dreamer v3 in pytorch.
episodic-transformer-memory-ppo
Clean baseline implementation of PPO using an episodic TransformerXL memory
DecisionTransformerInterpretability
Interpreting how transformers simulate agents performing RL tasks
rl-starter-files
RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code
QAOA_class
Python implementation of the Quantum Approximate Optimization Algorithm (QAOA) for solving various optimization problems
WolfensteinPython
Raycast Wolfenstein in Python
Wolfenstein-3D-Clone
Wolfenstein 3D using OpenGL
wolfenstein-rl
Wolfenstein Game w/ Deep Reinforcement Learning
Deep-learning-based-hybrid-recommender-systems
Recommender System Final Project in Skoltech