Official repository of our paper "Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning" (NeurIPS 2024)

PyTorch implementation of SAC-Discrete.

A collection of MARL benchmarks based on TorchRL

Mean Field Multi-Agent Reinforcement Learning

Official inference repo for FLUX.1 models

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Collection of reinforcement learning algorithms

Neural Turing Machines (NTM) - PyTorch Implementation

Ultralytics YOLO11 🚀

SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms

Implementation of the POIS algorithm

Official implementation for the paper "Offline Meta RL - Identifiability Challenges and Effective Data Collection Strategies", NeurIPS 2021.

Massively parallel rigidbody physics simulation on accelerator hardware.

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

Aruco Marker Calibration and Pose Estimation using OpenCV in Python

Acceptance rates for the major AI conferences

Code for Stabilizing Off-Policy RL via Bootstrapping Error Reduction

Code for conservative Q-learning

The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

Count the MACs / FLOPs of your PyTorch model.

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

An offline deep reinforcement learning library

An elegant PyTorch offline reinforcement learning library for researchers.

Official code for "RAMBO: Robust Adversarial Model-Based Offline RL", NeurIPS 2022

The unofficial LaTeX Beamer template for presentation slides at Singapore Management University (SMU).

A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools.

Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.

Code for the paper Fine-Tuning Language Models from Human Preferences

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.