dynamics-learning

Official code for "OpenWAM: An Open Framework for Composable World-Action Models" (Stanford University)

Code for our RSS'21 paper: "Hamiltonian-based Neural ODE Networks on the SE(3) Manifold For Dynamics Learning and Control"

Pytorch Implementation of SimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning, ICRA 2021

Robotics: Science and Systems (RSS) 2025 | Action Flow Matching for Continual Robot Learning | Online and Non-episodic Robot Dynamics Model Refinement.

Code for "Dynamics Harmonics Analysis of Robotic Systems: Application in Data-Driven Koopman Modeling", enabling the modeling of symmetric dynamical systems with decomposed Koopman operators per each irrep type.

Project page for Back to the Future: Predicting Long-Horizon Dynamics with Retrospective Correction for Disturbance-Aware Retrieval (DARE), an anonymous ICRA 2027 submission.