Pinned Repositories
annotated_deep_learning_paper_implementations
🧑🏫 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit), optimizers (adam, radam, adabelief), gans(dcgan, cyclegan, stylegan2), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, etc. 🧠
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
Beispielprojekt_GTD_JavaFX_Variante_A
Binary-Classifier
This repository provides the code of a binary classifier that is well documented, tested and was part of the Kaggle: American Express - Default Prediction challenge.
episodic-transformer-memory-ppo
Clean baseline implementation of PPO using an episodic TransformerXL memory
Generative-Adversarial-Network
Generating Atari Images with WGANs in PyTorch
neroRL
Deep Reinforcement Learning Framework done with PyTorch
recurrent-ppo-truncated-bptt
Reincarnation-Reinforcement-Learning-via-Inverse-Reinforcement-Learning
Sudoku-Solver
This Python-based Sudoku Solver utilizes the Pygame library to visually demonstrate the process of solving Sudoku puzzles. It offers an engaging way to watch the backtracking algorithm in action.
Horrible22232's Repositories
Horrible22232/Generative-Adversarial-Network
Generating Atari Images with WGANs in PyTorch
Horrible22232/Binary-Classifier
This repository provides the code of a binary classifier that is well documented, tested and was part of the Kaggle: American Express - Default Prediction challenge.
Horrible22232/Reincarnation-Reinforcement-Learning-via-Inverse-Reinforcement-Learning
Horrible22232/Sudoku-Solver
This Python-based Sudoku Solver utilizes the Pygame library to visually demonstrate the process of solving Sudoku puzzles. It offers an engaging way to watch the backtracking algorithm in action.
Horrible22232/annotated_deep_learning_paper_implementations
🧑🏫 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit), optimizers (adam, radam, adabelief), gans(dcgan, cyclegan, stylegan2), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, etc. 🧠
Horrible22232/Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
Horrible22232/Beispielprojekt_GTD_JavaFX_Variante_A
Horrible22232/episodic-transformer-memory-ppo
Clean baseline implementation of PPO using an episodic TransformerXL memory
Horrible22232/GameGAN-NVIDIA
Horrible22232/neroRL
Deep Reinforcement Learning Framework done with PyTorch
Horrible22232/recurrent-ppo-truncated-bptt
Horrible22232/glm
OpenGL Mathematics (GLM)
Horrible22232/GON
Gradient Origin Networks - a new type of implicit generative model that is able to quickly learn a latent representation without an explicit encoder
Horrible22232/Horrible22232.github.io
Horrible22232/Never-Give-Up-Learning-Directed-Exploration-Strategies
Horrible22232/ponder-transformer
Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper
Horrible22232/SnakeGame-Codex
A simple snake game generated with the OpenAI Codex model
Horrible22232/Super-Mario
Super Mario in SDL 2.0