# Enhancing Sim2Real Transfer for Torque-Controlled Robots through Real2Sim Dynamics Estimation and Reinforcement Learning

arXiv: https://arxiv.org/abs/2608.22629 · HTML: https://mlsanity.com/paper/2608.22629/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 23 Aug 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 16 of 16)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey](https://mlsanity.com/paper/2009.13303/) (2020)
- [Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience](https://mlsanity.com/paper/1810.05687/) (2018)
- [Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics](https://mlsanity.com/paper/2005.04269/) (2020)
- [Auto-Tuned Sim-to-Real Transfer](https://mlsanity.com/paper/2104.07662/) (2021)
- [Reinforcement Learning on Variable Impedance Controller for High-Precision Robotic Assembly](https://mlsanity.com/paper/1903.01066/) (2019)
- [Torque-based Deep Reinforcement Learning for Task-and-Robot Agnostic Learning on Bipedal Robots Using Sim-to-Real Transfer](https://mlsanity.com/paper/2304.09434/) (2023)
- [DROPO: Sim-to-Real Transfer with Offline Domain Randomization](https://mlsanity.com/paper/2201.08434/) (2022)
- [Sim2Real2Sim: Bridging the Gap Between Simulation and Real-World in Flexible Object Manipulation](https://mlsanity.com/paper/2002.02538/) (2020)
- [Selecting and Composing Learning Rate Policies for Deep Neural Networks](https://mlsanity.com/paper/2210.12936/) (2022)
- [A User's Guide to Calibrating Robotics Simulators](https://mlsanity.com/paper/2011.08985/) (2020)
- [DiAReL: Reinforcement Learning with Disturbance Awareness for Robust Sim2Real Policy Transfer in Robot Control](https://mlsanity.com/paper/2306.09010/) (2023)
- [Sim-to-Real gap in RL: Use Case with TIAGo and Isaac Sim/Gym](https://mlsanity.com/paper/2403.07091/) (2024)

## Abstract (arXiv)

Transferring reinforcement learning policies from simulation to Real-World robots remains a major challenge, particularly when dealing with low-level torque control, where even small modelling inaccuracies can lead to unstable or unsafe behaviours. In this work, we propose a Real2Sim2Real pipeline that improves Sim2Real transfer for torque-controlled robotic arms by combining trajectory matching, parameter optimization via genetic algorithms, and domain randomization. Using the 7-DOF Franka Emika Panda robot, we first identify friction, inertia, and gravity compensation parameters by minimizing the error between real and simulated joint trajectories. These calibrated dynamics are then used to train a TQC-based reinforcement learning agent in simulation. The trained policy is evaluated in both Gazebo and MuJoCo environments, and finally deployed on the real robot. Our results demonstrate a significant improvement in tracking accuracy and policy robustness after parameter tuning, with smooth policy transfer from simulation to the Real-World across multiple target-reaching tasks. This work highlights the effectiveness of accurate physical modelling in enabling stable and generalizable torque-based reinforcement learning policies.