Model-Free reinforcement learning with continuous action in practice

@article{Degris2012ModelFreeRL,
  title={Model-Free reinforcement learning with continuous action in practice},
  author={T. Degris and P. Pilarski and R. Sutton},
  journal={2012 American Control Conference (ACC)},
  year={2012},
  pages={2177-2182}
}
Reinforcement learning methods are often considered as a potential solution to enable a robot to adapt to changes in real time to an unpredictable environment. However, with continuous action, only a few existing algorithms are practical for real-time learning. In such a setting, most effective methods have used a parameterized policy structure, often with a separate parameterized value function. The goal of this paper is to assess such actor-critic methods to form a fully specified practical… Expand
Quadratic Q-network for Learning Continuous Control for Autonomous Vehicles
Automated Driving Maneuvers under Interactive Environment based on Deep Reinforcement Learning
OFFER: Off-Environment Reinforcement Learning
Setting up a Reinforcement Learning Task with a Real-World Robot
Real-time prediction learning for the simultaneous actuation of multiple prosthetic joints
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 20 REFERENCES
Reinforcement Learning in Continuous Time and Space
  • K. Doya
  • Mathematics, Medicine
  • Neural Computation
  • 2000
Stochastic policy gradient reinforcement learning on a simple 3D biped
  • Russ Tedrake, T. Zhang, H. Seung
  • Engineering, Computer Science
  • 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566)
  • 2004
Natural Actor-Critic
Policy Gradient Methods for Reinforcement Learning with Function Approximation
Natural actor-critic algorithms
Reinforcement Learning: An Introduction
Online human training of a myoelectric prosthesis controller via actor-critic reinforcement learning
Direct gradient-based reinforcement learning
  • J. Baxter, P. Bartlett
  • Mathematics, Computer Science
  • 2000 IEEE International Symposium on Circuits and Systems. Emerging Technologies for the 21st Century. Proceedings (IEEE Cat No.00CH36353)
  • 2000
Policy gradient reinforcement learning for fast quadrupedal locomotion
  • Nate Kohl, P. Stone
  • Computer Science, Engineering
  • IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004
  • 2004
...
1
2
...