Stars
TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM gateway, observability, optimization, evaluation, and experimentation.
Simplifying reinforcement learning for complex game environments
DSPy: The framework for programming—not prompting—language models
Really Fast End-to-End Jax RL Implementations
[arXiv] What-If Motion Prediction for Autonomous Driving ❓🚗💨
[CoRL'22] PlanT: Explainable Planning Transformers via Object-Level Representations
A data-driven, fast driving simulator for multi-agent coordination under partial observability.
Learning Off-Policy with Online Planning [CoRL 2021 Best Paper Finalist]
Pytorch version of Dreamer, which follows the original TF v2 codes.
Pytorch implementation of Dreamer-v2: Visual Model Based RL Algorithm.
Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.
PyTorch Implementation of the Maximum a Posteriori Policy Optimisation
Simple implementation of V-MPO proposed in https://arxiv.org/abs/1909.12238
(ICCV 2021, Oral) RL and distillation in CARLA using a factorized world model
Official GitHub repository for Argoverse dataset
Driving in CARLA using model-free deep reinforcement learning
Learning Invariant Representations for Reinforcement Learning without Reconstruction
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
An offline deep reinforcement learning library
The "Python Machine Learning (2nd edition)" book code repository and info resource
a contextual, biasable, word-or-sentence-or-paragraph extractive summarizer powered by the latest in text embeddings (Bert, Universal Sentence Encoder, Flair)
🎯 A comprehensive gradient-free optimization framework written in Python