Reinforcement learning has shown great promise in robotics thanks to its ability to develop efficient robotic control procedures through self-training. In particular, reinforcement learning has been successfully applied to solving the reaching task with robotic arms. In this paper, we define a robust, reproducible and systematic experimental procedure to compare the performance of various model-free algorithms at solving this task. The policies are trained in simulation and are then transferred to a physical robotic manipulator. It is shown that augmenting the reward signal with the Hindsight Experience Replay exploration technique increases the average return of off-policy agents between 7 and 9 folds when the target position is initialised randomly at the beginning of each episode.
@article{arxiv.2011.05782,
title = {Reinforcement Learning Experiments and Benchmark for Solving Robotic Reaching Tasks},
author = {Pierre Aumjaud and David McAuliffe and Francisco Javier Rodríguez Lera and Philip Cardiff},
journal= {arXiv preprint arXiv:2011.05782},
year = {2020}
}