This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Autopilot Strategy Based on Improved DDPG Algorithm
ISSN: 0148-7191, e-ISSN: 2688-3627
Published November 04, 2019 by SAE International in United States
This content contains downloadable datasetsAnnotation ability available
Deep Deterministic Policy Gradient (DDPG) is one of the Deep Reinforcement Learning algorithms. Because of the well perform in continuous motion control, DDPG algorithm is applied in the field of self-driving. Regarding the problems of the instability of DDPG algorithm during training and low training efficiency and slow convergence rate. An improved DDPG algorithm based on segmented experience replay is presented. On the basis of the DDPG algorithm, the segmented experience replay select the training experience by the importance according to the training progress to improve the training efficiency and stability of the training model. The algorithm was tested in an open source 3D car racing simulator called TORCS. The simulation results demonstrate the training stability is significantly improved compared with the DDPG algorithm and the DQN algorithm, and the average return is about 46% higher than the DDPG algorithm and about 55% higher than the DQN algorithm.
CitationTian, Z., Zuo, X., and Li, X., "Autopilot Strategy Based on Improved DDPG Algorithm," SAE Technical Paper 2019-01-5072, 2019, https://doi.org/10.4271/2019-01-5072.
Data Sets - Support Documents
|[Unnamed Dataset 1]|
|[Unnamed Dataset 2]|
|[Unnamed Dataset 3]|
- Chenjia, B.A.I. , Research on Autonomous Driving Method Based on Computer Vision and Deep Learning (Harbin Institute of Technology, 2017), 70-73.
- Sallab, A. et al. , “Deep Reinforcement Learning Framework for Autonomous Driving,” Electronic Imaging 2017(19):70-76, 2017.
- Sallab, A.E. et al. , “End-to-End Deep Reinforcement Learning for Lane Keeping Assist,” arXiv preprint arXiv:1612.04340, 2016.
- Xia, W.L. et al. , “Training Method of Automatic Driving Strategy Based on Deep Reinforcement Learning,” Journal of Integration Technology 3:29-35, 2017.
- Lillicrap, T.P., Hunt, J.J., Pritzel, A. et al. , “Continuous Control with Deep Reinforcement Learning,” arXiv preprint arXiv:1509. 02971, 2016.
- Silver, D. et al. , “Deterministic Policy Gradient Algorithms,” in ICML, 2014.
- Schaul, T. et al. , “Prioritized Experience Replay,” arXiv preprint arXiv:1511.05952, 2015.
- Rausch, V., Hansen, A., Solowjow, E. et al. , “Learning a Deep Neural Net Policy for End-to-End Control of Autonomous Vehicles,” in AACC, 2017.
- Lin, L.J. . “Reinforcement Learning for Robots Using Neural Networks,” Carnegie-Mellon Univ Pittsburgh PA School of Computer Science, 1993.