Reinforcement learning models trained only in simulation using automatic domain randomization solve Rubik's cube with a real robot hand.
Sim-to-Real Transfer of Robotic Control with Dynamics Randomization
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Simulations are attractive environments for training agents as they provide an abundant source of data and alleviate certain safety concerns during the training process. But the behaviours developed by agents in simulation are often specific to the characteristics of the simulator. Due to modeling error, strategies that are successful in simulation may not transfer to their real world counterparts. In this paper, we demonstrate a simple method to bridge this "reality gap". By randomizing the dynamics of the simulator during training, we are able to develop policies that are capable of adapting to very different dynamics, including ones that differ significantly from the dynamics on which the policies were trained. This adaptivity enables the policies to generalize to the dynamics of the real world without any training on the physical system. Our approach is demonstrated on an object pushing task using a robotic arm. Despite being trained exclusively in simulation, our policies are able to maintain a similar level of performance when deployed on a real robot, reliably moving an object to a desired location from random initial configurations. We explore the impact of various design decisions and show that the resulting policies are robust to significant calibration error.
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
EPI policies use a transition-predictability reward to probe environments and condition task policies, outperforming standard generalization methods on novel test environments.
Isaac Lab is a unified GPU-native platform combining high-fidelity physics, photorealistic rendering, multi-frequency sensors, domain randomization, and learning pipelines for scalable multi-modal robot policy training.
Q-guided reverse-time flow sampling with a rollout-trained action-chunk critic improves frozen SmolVLA success on LIBERO, with strong single-task gains but only modest locked held-out transfer.
Object-centric residual RL trained in simulation with pose noise and dropout raises real Franka robot VLA success from 42% to 76% zero-shot across five tasks, with improved data reusable for base model retraining.
Zero-shot sim-to-real transfer of independently trained RL policies for cart-pole swing-up and stabilization is achieved via sensitivity-guided domain randomization, linear curriculum learning, and first-order action smoothing with Simulink switching logic.
citing papers explorer
-
Solving Rubik's Cube with a Robot Hand
Reinforcement learning models trained only in simulation using automatic domain randomization solve Rubik's cube with a real robot hand.
-
Environment Probing Interaction Policies
EPI policies use a transition-predictability reward to probe environments and condition task policies, outperforming standard generalization methods on novel test environments.
-
Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
Isaac Lab is a unified GPU-native platform combining high-fidelity physics, photorealistic rendering, multi-frequency sensors, domain randomization, and learning pipelines for scalable multi-modal robot policy training.
-
Guided Action Flow: Q-Guided Inference for Flow-Matching Vision-Language-Action Policies
Q-guided reverse-time flow sampling with a rollout-trained action-chunk critic improves frozen SmolVLA success on LIBERO, with strong single-task gains but only modest locked held-out transfer.
-
Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement
Object-centric residual RL trained in simulation with pose noise and dropout raises real Franka robot VLA success from 42% to 76% zero-shot across five tasks, with improved data reusable for base model retraining.
-
Zero-shot Transfer of Reinforcement Learning Control Policies for the Swing-Up and Stabilization of a Cart-Pole System
Zero-shot sim-to-real transfer of independently trained RL policies for cart-pole swing-up and stabilization is achieved via sensitivity-guided domain randomization, linear curriculum learning, and first-order action smoothing with Simulink switching logic.