Autor: |
Aumjaud, Pierre, McAuliffe, David, Lera, Francisco Javier Rodríguez, Cardiff, Philip |
Rok vydání: |
2020 |
Předmět: |
|
Zdroj: |
Advances in Intelligent Systems and Computing, 1285 (2021), 318-331 |
Druh dokumentu: |
Working Paper |
DOI: |
10.1007/978-3-030-62579-5_22 |
Popis: |
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. |
Databáze: |
arXiv |
Externí odkaz: |
|