bc

ABC: Scalable Behavior Cloning with Open Data, Training, and Evaluation

D2C(Data-driven Control Library) is a library for data-driven control based on reinforcement learning.

实机部署so101流程和踩坑全记录，使用lerobot框架so101真机。在本地 ubuntu22+5070显卡 搭建环境，部署，录数据，训练smolvla，推理全流程。

SwapTransformer: Highway Overtaking Tactical Planner Model via Imitation Learning on OSHA Dataset

c99/Python frameworks to solve ODEs using arbitrary order Power Series Method (arbitrary precision with GNU MPFR), validate solutions using Clean Numerical Simulation, and plot bifurcation diagrams. Plus n-body simulations using composed symplectic integrators. OpenGL (legacy) 3D plotting. No Wayland support, for ever, and no "a1".

实机部署so101流程和踩坑全记录，使用lerobot框架以及isaaclab（issac sim）在虚拟环境跑通so101。在本地 ubuntu22+5070显卡 搭建环境，部署，录数据，训练smolvla，推理全流程。

A repository containing a module for the BCWS fuel typing algorithm, and a scripted GUI that allows users to easily calculate fuel types for the BC VRI dataset, or from plot-level stand structure data.

Offline Reinforcement Learning Framework

BC Ferries GraphQL API & scraper

Implement of Behavior Cloning (BC) and Conservative Q-Learning (CQL) algorithms for training reinforcement learning models using a dataset of state-action pairs. It provides an environment for experimenting with these algorithms, comparing their performance, and analyzing the effects of different parameters and dataset variations on training result

CLI Calculator with matrices transformations, functions/equations solver, complex numbers...