Efficient deep reinforcement learning in robotic motion planning
Robot motion planning requires solutions to several challenges: Imbalanced data distribution, multi-objective optimization, the curse of dimensionality, and the 'Sim2Real' gap, i.e., the differences between the simulated and the physical world. Instead of programming specific algorithms to navigate such challenges, machine learning is often used, and in particular reinforcement learning (RL). Then, the robot learns to perform a particular task by trial and error, being rewarded for appropriate actions and punished for making errors.
In her PhD, Sha Luo investigated how curriculum learning, learning with planning, imitation learning, and a hierarchical setup of the learning process could help to improve the Reinforcement Learning (RL) training efficiency and robustness in robotic motion planning tasks. She found that these methods all played a positive role in improving the sampling efficiency and task performance in the motion planning tasks. Using a guidance mechanism that improves the probability of positive experiences in task exploration appeared to contribute most to improved performance.