Dynamic Mirror Descent based Model Predictive Control for Accelerating Robot 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 hardware setting, thereby validating the proposed approach.

Authors

• Utkarsh A. Mishra
• Soumya R. Samineni
• Prakhar Goel
• Chandravaran Kunjeti
• Himanshu Lodha
• Aman Singh
• Aditya Sagi
• Shalabh Bhatnagar
• Shishir Kolathaya

Keywords

• Training
• Legged locomotion
• Heuristic algorithms
• Predictive models
• Prediction algorithms
• Hardware
• Quadrupedal robots
• Model Predictive Control
• Mirror Descent
• Online Learning
• Outer Loop
• Reinforcement Learning Algorithm
• Hierarchical Framework
• Model-free Reinforcement Learning
• Model-based Reinforcement Learning
• Learning Algorithms
• Value Function
• Efficient Algorithm
• Complex Dynamics
• Control Sequence
• Optimal Policy
• Sampling Efficiency
• Inertial Measurement Unit
• Shift Operator
• Reward Function
• Markov Decision Process
• Complex Dynamic Systems
• Horizon Length
• Bregman Divergence
• Exponential Family
• Terminal Cost
• Stochastic Policy
• Reinforcement Learning Policy