Search Results for "opened dynamics engine"

VERL is a reinforcement-learning–oriented toolkit designed to train and align modern AI systems, from language models to decision-making agents. It brings together supervised fine-tuning, preference modeling, and online RL into one coherent training stack so teams can move from raw data to aligned policies with minimal glue code. The library focuses on scalability and efficiency, offering distributed training loops, mixed precision, and replay/buffering utilities that keep accelerators busy....

mujoco-py is a Python wrapper for MuJoCo, a high-performance physics engine widely used in robotics, reinforcement learning, and AI research. It allows developers and researchers to run detailed rigid body simulations with contacts directly from Python, making MuJoCo easier to integrate into machine learning workflows. The library is compatible with MuJoCo version 2.1 and supports Linux and macOS, while Windows support has been deprecated. It provides utilities for loading models, running...

EVO is a simulation platform for co-evolving the morphology and the behavior of 3D artificial agents in a complex environment. This project directly follows the original work of Karl Sims. It puts together complex creatures, a GA & Open Dynamics Engine.

Todbot is an AI addon to the gamestool virtual machine. The aim is to create an evolving neural network topology that should be capable of creating the optimal topology and network weighting to solve any problem given it.

A C++ framework and applications for experimenting with artificial intelligence, 3D graphics and simulated physics. It's primary focus is to provide a testbed for simulated robotics using Ogre 3D and the Open Dynamics Engine.

The Athlete is a virtual robot living in the ODE (Open Dynamics Engine)world. An evolution algorithm is implemented based on the DR-EA-M to optimize its performances. This involves a Genetic algorithm, network of neurons and morphology. All is in java.

The DragonBreath Engine is a constraint solver based on local search. It features real-time computation, handling of dynamics, structural constraint satisfaction, and an easy way to include domain-specific knowledge.