- Cupertino, USA
- https://alex-petrenko.github.io/
- @petrenko_ai
Stars
Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"
Intrinsic Motivation from Artificial Intelligence Feedback
Learn online intrinsic rewards from LLM feedback
Code for BEHRT: Transformer for Electronic Health Records
Python suite to construct benchmark machine learning datasets from the MIMIC-III 💊 clinical database.
A customizable pipeline for data extraction from MIMIC-IV.
1 million FPS multi-agent driving simulator
Simplifying reinforcement learning for complex game environments
MIMIC Code Repository: Code shared by the research community for the MIMIC family of databases
A high-throughput and memory-efficient inference and serving engine for LLMs
Streamlit component that allows you to copy text to clipboard
A Streamlit component to show calendar view using FullCalendar
Aerial Gym Simulator - Isaac Gym Simulator for Aerial Robots
Curiosity-driven Exploration by Self-supervised Prediction
Evolutionary Scale Modeling (esm): Pretrained language models for proteins
A bare-bones Python library for quality diversity optimization.
AI Plays Trackmania with Reinforcement Learning
NNRUG / it52-rails
Forked from vtambourine/it61-railsСайт нижегородского IT-сообщества
High performance simulation for robotic tasks with granular materials
Press the 'f' and 'd' keys randomly. It's easy. Just use your "free will."