A Survey on Policy Search for Robotics

@article{Deisenroth2013ASO,
  title={A Survey on Policy Search for Robotics},
  author={M. Deisenroth and G. Neumann and Jan Peters},
  journal={Found. Trends Robotics},
  year={2013},
  volume={2},
  pages={1-142}
}
Policy search is a subfield in reinforcement learning which focuses on finding good parameters for a given policy parametrization. [...] Key Method We classify model-free methods based on their policy evaluation strategy, policy update strategy, and exploration strategy and present a unified view on existing algorithms. Learning a policy is often easier than learning an accurate forward model, and, hence, model-free methods are more frequently used in practice. However, for each sampled trajectory, it is…Expand
A Survey on Policy Search Algorithms for Learning Robot Controllers in a Handful of Trials
Black-box data-efficient policy search for robotics
Actor-Critic PAC Robust Policy Search
Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics
Model-based contextual policy search for data-efficient generalization of robot skills
PLATO: Policy learning using adaptive trajectory optimization
Reinforcement Learning
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 111 REFERENCES
Autonomous helicopter control using reinforcement learning policy search methods
  • J. Bagnell, J. Schneider
  • Engineering, Computer Science
  • Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164)
  • 2001
State-Dependent Exploration for Policy Gradient Methods
Policy Search for Motor Primitives in Robotics
Least-Squares Policy Iteration
Infinite-Horizon Policy-Gradient Estimation
...
1
2
3
4
5
...