Adaptive Probabilistic Trajectory Optimization via Efficient Approximate Inference
This work addresses robotic control in dynamic environments, presenting an incremental improvement by hybridizing existing approaches.
The paper tackles the problem of robotic decision-making in uncertain environments by proposing adaptive probabilistic trajectory optimization, which combines Reinforcement Learning and Model Predictive Control to achieve faster convergence and robustness. The method demonstrated effectiveness and efficiency on three learning tasks.
Robotic systems must be able to quickly and robustly make decisions when operating in uncertain and dynamic environments. While Reinforcement Learning (RL) can be used to compute optimal policies with little prior knowledge about the environment, it suffers from slow convergence. An alternative approach is Model Predictive Control (MPC), which optimizes policies quickly, but also requires accurate models of the system dynamics and environment. In this paper we propose a new approach, adaptive probabilistic trajectory optimization, that combines the benefits of RL and MPC. Our method uses scalable approximate inference to learn and updates probabilistic models in an online incremental fashion while also computing optimal control policies via successive local approximations. We present two variations of our algorithm based on the Sparse Spectrum Gaussian Process (SSGP) model, and we test our algorithm on three learning tasks, demonstrating the effectiveness and efficiency of our approach.