Dynamic Mirror Descent MPC for Model-based Model-free Reinforcement Learning

Dynamic Mirror Descent MPC for Model-based Model-free Reinforcement Learning


Recent works in Reinforcement Learning (RL) combine model-free (Mf)-RL algorithms with model-based (Mb)-RL approaches to get the best from both: asymptotic performance of Mf-RL and high sample-efficiency of Mb-RL. Inspired by these works, we propose a hierarchical framework that integrates online learning for the Mb-trajectory optimization with off-policy methods for the Mf-RL. In particular, two loops are proposed, where the Dynamic Mirror Descent based Model Predictive Control (DMD-MPC) is used as the inner loop Mb-RL to obtain an optimal sequence of actions. These actions are in turn used to significantly accelerate the outer loop Mf-RL. We show that our formulation is generic for a broad class of MPC-based policies and objectives, and includes some of the well-known Mb-Mf approaches. We finally introduce a new algorithm: Mirror-Descent Model Predictive RL (M-DeMoRL), which uses Cross-Entropy Method (CEM) with elite fractions for the inner loop. Our experiments show faster convergence of the proposed hierarchical approach on benchmark MuJoCo tasks. We also demonstrate hardware training for trajectory tracking in a 2R leg and hardware transfer for robust walking in a quadruped. We show that the inner-loop Mb-RL significantly decreases the number of training iterations required in the real system, thereby validating the proposed approach.

Fore more references, refer to paper at arxiv.org/pdf/2112.02999.pdf and code at github.com/UtkarshMishra04/DMD-MPC-RL

Control Framework


Simulation Results

Hardware Results



    title={Dynamic Mirror Descent based Model Predictive Control for Accelerating Robot Learning},
    author={Mishra, Utkarsh A, Samineni, Soumya R, Goel, Prakhar, Kunjeti, Himanshu, Lodha, Aman, Singh, Aditya, Sagi, Shalabh, Bhatnagar, and Kolathaya, Shishir},
    journal={arXiv preprint arXiv:2106.15273},

Related Papers

PDF Dynamic Mirror Descent based Model Predictive Control for Accelerated Robot Learning
Utkarsh A Mishra, Soumya Rani, Prakhar Goel, Chandravaran Kunjeti, Himanshu Lodha, Aman Singh, Aditya Sagi, Shalabh Bhatnagar, and Shishir Kolathaya
IEEE International Conference on Robotics and Automation (ICRA) 2022, Philadelphia, USA


Soumya Rani
MTech CSA, 2021, Now at Quantiphi
Prakhar Goel
Now at Chirathe Robotics
Shishir Kolathaya (HEAD)
Assistant Professor
Last updated: 2022-01-31