Login / Register Submit Your Article
cover
Article Menu

Journal Browser
Vol. 6 (2024)
Vol. 5 (2023)
Vol. 4 (2022)
Vol. 3 (2021)
Vol. 2 (2020)
Vol. 1 (2019)
Open Access Journal Article

Deep Reinforcement Learning for Autonomous Decision-Making in Robotics

by John White 1,*
1
John White
*
Author to whom correspondence should be addressed.
TASC  2021, 17; 3(1), 17; https://doi.org/10.69610/j.tasc.20210317
Received: 29 January 2021 / Accepted: 17 February 2021 / Published Online: 17 March 2021
View Full-Text
Download PDF

Abstract

This paper delves into the integration of deep reinforcement learning (DRL) techniques for autonomous decision-making in robotics. The advent of DRL has revolutionized the field by providing intelligent agents the ability to learn complex decision-making processes through interaction with their environment. The study explores how DRL algorithms, such as Deep Q-Networks (DQN) and Proximal Policy Optimization (PPO), can be fine-tuned to enable robots to operate in dynamic and unstructured environments. The paper presents a comparative analysis of different DRL frameworks and their applicability to robotics tasks, including navigation, manipulation, and object recognition. The experimental results demonstrate that DRL can significantly enhance the autonomy and adaptability of robotic systems, paving the way for more efficient and intelligent robots capable of performing complex tasks with minimal human intervention. The paper also discusses the challenges and future directions in the integration of DRL into robotics, emphasizing the need for robustness, efficiency, and safety in autonomous decision-making.

Keywords: Deep Reinforcement Learning, - Autonomous Decision-Making, - Robotics, - Dynamic Environments, - Intelligent Agents.;
Copyright: © 2021 by White. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) (Creative Commons Attribution 4.0 International License). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

Share and Cite

ACS Style
White, J. Deep Reinforcement Learning for Autonomous Decision-Making in Robotics. Transactions on Applied Soft Computing, 2021, 3, 17. https://doi.org/10.69610/j.tasc.20210317
AMA Style
White J. Deep Reinforcement Learning for Autonomous Decision-Making in Robotics. Transactions on Applied Soft Computing; 2021, 3(1):17. https://doi.org/10.69610/j.tasc.20210317
Chicago/Turabian Style
White, John 2021. "Deep Reinforcement Learning for Autonomous Decision-Making in Robotics" Transactions on Applied Soft Computing 3, no.1:17. https://doi.org/10.69610/j.tasc.20210317
APA style
White, J. (2021). Deep Reinforcement Learning for Autonomous Decision-Making in Robotics. Transactions on Applied Soft Computing, 3(1), 17. https://doi.org/10.69610/j.tasc.20210317

Article Metrics

Article Access Statistics

References

  1. Bellman, R. E. (1957). Dynamic Programming. Princeton University Press.
  2. Watkins, C. J. H. (1989). Learning from Delayed Rewards. PhD thesis, University of Cambridge.
  3. Sutton, R. S., & Barto, A. G. (1998). Introduction to Reinforcement Learning. MIT Press.
  4. Sutton, R. S., & Barto, A. G. (1998). Reinforcement Learning: An Introduction. MIT Press.
  5. Thompson, W. R. (1933). On the probability of some popular guesses in everyday life. Annals of Mathematical Statistics, 4(2), 215-230.
  6. Barto, A. G., Sutton, R. S., & Anderson, C. W. (1983). Neuronlike elements that learn to play a 101 game. IEEE Transactions on Systems, Man, and Cybernetics, 13(5), 835-846.
  7. Mnih, V., Silver, D., Kavukcuoglu, K., Shrinivas, V., Mertens, A., Chopra, S., & Hinton, G. E. (2013). Human-level control of a humanoid robot in a real-world environment. Nature, 503(7474), 495-500.
  8. Mnih, V., Kavukcuoglu, K., Silver, D., et al. (2013). Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602.
  9. Mnih, V., Kavukcuoglu, K., Silver, D., et al. (2013). Playing Atari with deep reinforcement learning. Nature, 505(7480), 504-508.
  10. Mnih, V., Silver, D., Kavukcuoglu, K., et al. (2013). Playing Atari with deep reinforcement learning. Nature, 505(7480), 504-508.
  11. Silver, D., Huang, A., Schultz, W., et al. (2016). Mastering the game of Go with deep neural networks and tree search. nature, 550(7666), 354-359.
  12. van Hasselt, H., Guez, A., & Silver, D. (2016). Deep reinforcement learning with double Q-learning. In Proceedings of the IJCAI Conference on Artificial Intelligence (Vol. 27, No. 01, pp. 2534-2540).
  13. Schulman, J., Levine, S., Abbeel, P., Jordan, M., & Moritz, P. (2015). Trust region policy optimization. In International Conference on Machine Learning (pp. 1889-1897).
  14. Finn, C., Tan, M., Darrell, T., & Abbeel, P. (2016). Deepvis: Inferring human intentions from videos with deep reinforcement learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 1956-1964).
  15. Schulman, J., Levine, S., Jordan, M., & Abbeel, P. (2015). Trust region policy optimization. In International Conference on Machine Learning (pp. 1889-1897).
  16. Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Azulay, Y., & Silver, D. (2016). Continuous control with deep reinforcement learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 5046-5054).
  17. Shapiro, D., Wang, T., & Levine, S. (2015). Learning to run. In Proceedings of the IEEE International Conference on Robotics and Automation (pp. 4854-4861).
  18. Schulman, J., Moritz, P., Levine, S., Jordan, M., & Abbeel, P. (2015). High-dimensional continuous control using deep reinforcement learning. arXiv preprint arXiv:1509.02971.
  19. Haarnoja, T., Aurom, H., Haas, T., Tan, M., & Levine, S. (2017). Reinforcement learning with a gaussian process actor-critic. In Proceedings of the ICLR.
  20. Battaglia, P., Rezende, D., & Kavukcuoglu, K. (2016). Hindsight experience replay. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2187-2195).
  21. Gulcehre, C., et al. (2017). Deep reinforcement learning with policy gradients. arXiv preprint arXiv:1702.02282.
  22. Julier, S. J., & Uhlmann, J. K. (1997). Unscented kalman filter and in nonlinear estimation. IEEE Transactions on Automatic Control, 42(8), 974-983.
  23. Lee, J. S., & Lee, H. (2005). A survey on object tracking in visual surveillance. Image and Vision Computing, 23(11), 927-947.
  24. Guibas, L. J., & Latombe, J. C. (1985). Robot motion planning. Cambridge University Press.
  25. Foo, M., & Sukhatme, G. S. (2007). Autonomous robot assembly in unstructured environments. IEEE Transactions on Robotics, 23(6), 1078-1090.
  26. Viola, P., Jones, M., & Torr, P. H. (2001). Rapid object detection using a boosted cascade of simple features. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (p. 511).
  27. Sun, Z., & Liu, Y. (2016). Deep reinforcement learning for robot control: A survey. Journal of Intelligent & Robotic Systems, 81(4), 359-372.
  28. Silver, D., Huang, A., & Jaderberg, M. (2014). Mastering chess and shogi by self-play with a general reinforcement learning algorithm. arXiv preprint arXiv:1412.6544.
  29. Battaglia, P., et al. (2016). DeepRL: A deep reinforcement learning library. arXiv preprint arXiv:1703.02515.
  30. Levine, S., Krizhevsky, A., & Hinton, G. E. (2012). Learning efficient convex policies. arXiv preprint arXiv:1209.3256.