Akarsh Rastogi's repositories
awesome-courses
:books: List of awesome university courses for learning Computer Science!
reinforcement-learning
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
Detectron2-train
Detectron2 Trainer framework for Medical Imaging
imitation-learning
Clean PyTorch implementations of imitation and reward learning algorithms
Magellan-Simulation
Visualized 2D dynamics simulation for Subways, public transport and paths within a dynamic city
MLP-Mixer-trainer
A framework for conducting training experiments with Mixers, an efficient alternative to Vision Transformers (ViTs)
multiagent-gail
Testing Multi-Agent Generative Adversarial Imitation Learning (GAIL)
ARENA_2.0
Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
awesome-ai-safety
A curated list of awesome AI safety papers, projects and communities.
coding-interview-university
A complete computer science study plan to become a software engineer.
ControlGAN
Pytorch implementation for Controllable Text-to-Image Generation.
Deep_reinforcement_learning_Course
Implementations from the free course Deep Reinforcement Learning with Tensorflow
dify-LLMAgents
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
DQN-Flappy-Bird
🕹️ Flappy Bird hack using Deep Reinforcement Learning with Double Q-learning
eng-practices
Google's Engineering Practices documentation
reinforcement-learning-an-introduction
Python Implementation of Reinforcement Learning: An Introduction
Supermathematics-and-Artificial-General-Intelligence
I clearly unravel how I came to invent the supermanifold hypothesis in deep learning, (a part of a system called 'thought curvature') in relation to quantum computation.
Vision-language-models-as-RL-rewards
Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning Paper implementation by Anthropic / FAR AI