Deep learning and especially deep reinforcement learning usually require huge amount of data for training and simulators using is perspective approach to provide this data. Model trained in simulator can be transferred on real robot without wasting a lot of time to collect data. Training in simulator also allows using of different techniques to speed up convergence and increase resulting performance. One of them is to train feature-based model with access to the whole information about the environment and use it as expert for main image-based model. This reduces earning time and the computational costs that are necessary to obtain quality results with image-based model. In this work we improve idea of behaviour cloning feature agent and make it more flexible with using of expert demonstrations forgetting. We conducted experiments on transfer learning for a robotic manipulator that interacts with complex objects and compared them with classic off-policy approaches.
Скачать PDF или читать онлайн на ScienceDirect (англ.): https://www.sciencedirect.com/science/article/pii/S187705092100990X
Айтыгулов Э., Панов А. И. Transfer Learning with Demonstration Forgetting for Robotic Manipulator // Procedia Computer Science, Vol. 186, pp. 374–380.