Tag
Real2Gym is an agentic Real2Sim2Real framework that transforms human and robot video demonstrations into interactive simulation gyms, enabling skill transfer to physical robots with improved success rates over baselines.
Pollen Robotics showcases Microduck, a robot and simulator with an open-source reinforcement learning stack, enabling sim2real training for AI agents.
A GitHub repository providing RL training environments for the Microduck bipedal robot, built on MuJoCo Warp with PPO, including sim2real deployment and reward modeling techniques.
An open-source reinforcement learning stack for the Microduck bipedal robot, enabling sim2real training and deployment using MuJoCo and PPO.
Pollen Robotics unveils Microduck, an open-source biped robot trainable with reinforcement learning, priced under $400, featuring pre-trained policies and a full open training stack.
Microduck is a tiny, open-source biped robot from Pollen Robotics that can be trained with reinforcement learning and is available for pre-order at $399.
Niantic Spatial, Flexion, and NVIDIA demonstrate a sim2real pipeline for humanoid robots using digital twins and RL, achieving zero-shot transfer from simulation to real office navigation.
Introduces digital teleoperation using action-conditioned world models to generate diverse training data for robotics, decoupling data collection from physical hardware. The system achieves real-time generation and enables zero-shot Sim2Real transfer.
Introducing ASPIRE, a framework for robots to continuously evolve a library of skills through evolutionary search and distillation, enabling efficient sim-to-real and cross-embodiment transfer with up to 10x reduction in transfer learning tokens. The full stack is open-sourced.
Wuji MJLab is an open-source MuJoCo environment for dexterous hand manipulation, featuring a cube reorientation task, sim2real pipeline, and deployment on the Wuji Hand. It is based on mjlab and includes pretrained PPO policies.
This GitHub repository provides reinforcement learning training environments for the Microduck bipedal robot, using MuJoCo Warp and PPO with a sim2real deployment pipeline.