Reinforcement Learning for Autonomous Systems: Practical Implementations in Robotics
Keywords:
Reinforcement Learning, Robotics, Sample EfficiencyAbstract
RL improves autonomous robot navigation, control, and manipulation. This article covers autonomous robotic system RL theory and methodologies. Robotics research includes Q-learning, DQN, and policy gradient.
Model-free Multiple robots Q-learning helps RL applications choose the optimum value estimate method. Q-learning excels at discrete actions but not continuous ones. DQNs improve Q-value function using deep neural networks. Advanced robotics benefit from high-dimensional state spaces. RL.
References
R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed. Cambridge, MA: MIT Press, 2018.
C. M. Bishop, Pattern Recognition and Machine Learning. New York, NY: Springer, 2006.
M. Mnih et al., “Human-level control through deep reinforcement learning,” Nature, vol. 518, no. 7540, pp. 529–533, Feb. 2015.
V. Mnih et al., “Asynchronous actor-critic methods,” arXiv preprint arXiv:1602.01783, 2016.
J. Schulman et al., “Trust region policy optimization,” arXiv preprint arXiv:1502.05477, 2015.
Y. Duan et al., “Benchmarking deep reinforcement learning for continuous control,” arXiv preprint arXiv:1604.06778, 2016.
D. Silver et al., “Mastering the game of Go with deep neural networks and tree search,” Nature, vol. 529, no. 7587, pp. 484–489, Jan. 2016.
J. Peters and S. Schaal, “Reinforcement learning of motor skills with policy gradients,” Neural Networks, vol. 21, no. 4, pp. 682–697, May 2008.
C. Hsu et al., “Deep Q-learning for robot navigation,” Journal of Robotics and Automation, vol. 3, no. 1, pp. 10–22, Jan. 2020.
M. Zhan et al., “A survey on reinforcement learning algorithms and their applications in robotics,” IEEE Access, vol. 8, pp. 190829–190846, 2020.
S. Levine et al., “End-to-end training of deep visuomotor policies,” Journal of Machine Learning Research, vol. 17, no. 1, pp. 1–40, 2016.
A. J. Barto, “Temporal difference learning and TD-Gammon,” Communications of the ACM, vol. 38, no. 3, pp. 35–38, Mar. 1995.
X. Chen et al., “Multi-agent reinforcement learning: A review,” IEEE Transactions on Cybernetics, vol. 51, no. 5, pp. 2399–2414, May 2021.
Z. Zhang and L. Liu, “Learning to coordinate in multi-agent systems using reinforcement learning,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 3, pp. 1125–1138, Mar. 2022.
R M. Li and D. Yang, “Safe and efficient exploration in reinforcement learning with probabilistic safety guarantees,” IEEE Transactions on Robotics, vol. 38, no. 2, pp. 563–577, Apr. 2022.
W. Xu, “Robust reinforcement learning with safety constraints: A survey,” IEEE Access, vol. 10, pp. 72480–72497, 2022.
D. Lee et al., “Hierarchical reinforcement learning for scalable robotics control,” IEEE Transactions on Automation Science and Engineering, vol. 15, no. 4, pp. 1572–1585, Oct. 2018.
M. Da Silva et al., “Leveraging generative models for reinforcement learning in robotics,” IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 3456–3463, Apr. 2021.
J.. and D. J. Chen and W. Hong, “Integrating reinforcement learning with unsupervised learning techniques for robotics,” IEEE Transactions on Machine Learning, vol. 25, no. 3, pp. 945–958, Mar. 2023.
H. Li, “Deep reinforcement learning for robotic grasping: A survey,” IEEE Access, vol. 9, pp. 212832–212845, 2021.
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
