Stars
A solver for nonlinear programming with GPU support
Official implementation for the paper "Full-Order Sampling-Based MPC for Torque-Level Locomotion Control via Diffusion-Style Annealing". DIAL-MPC is a novel sampling-based MPC framework for legged …
Exact Combinatorial Optimization with Graph Convolutional Neural Networks (NeurIPS 2019)
[Neurips 2024] A benchmark suite for autoregressive neural emulation of PDEs. (≥46 PDEs in 1D, 2D, 3D; Differentiable Physics; Unrolled Training; Rollout Metrics)
The repository is for safe reinforcement learning baselines.
Control Of Physics Informed Gaussian Processes.
Transforms your CasADi functions into batchable JAX-compatible functions. By combining the power of CasADi with the flexibility of JAX, JAXADi enables the creation of efficient code that runs smoot…
An Extensible Benchmarking Platform for Scalable Dynamical System Identification
tsl: a PyTorch library for processing spatiotemporal data.
Code for "SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning" by Zolman et al.
Supplementary Material "Co-Design Optimisation of Morphing Topology and Control of Winged Drones" published in IEEE 2024 International Conference on Robotics and Automation (ICRA)
Physics-informed Machine Learning for Modeling, Control, and Optimization at CDC 2024
Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.
Optax is a gradient processing and optimization library for JAX.
"Deep Generative Modeling": Introductory Examples
Productive, portable, and performant GPU programming in Python.
10 differentiable physical simulators built with Taichi differentiable programming (DiffTaichi, ICLR 2020)
BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.
A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.
A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git.
An experimental language for causal reasoning
Learning to Optimize with Proximal Operators (LOPO)
A flexible package manager that supports multiple versions, configurations, platforms, and compilers.