Corpus ID: 214612538

Safe Reinforcement Learning of Control-Affine Systems with Vertex Networks

@article{Zheng2020SafeRL,
  title={Safe Reinforcement Learning of Control-Affine Systems with Vertex Networks},
  author={L. Zheng and Yuanyuan Shi and L. Ratliff and B. Zhang},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.09488}
}
This paper focuses on finding reinforcement learning policies for control systems with hard state and action constraints. Despite its success in many domains, reinforcement learning is challenging to apply to problems with hard constraints, especially if both the state variables and actions are constrained. Previous works seeking to ensure constraint satisfaction, or safety, have focused on adding a projection step to a learned policy. Yet, this approach requires solving an optimization problem… Expand
2 Citations

References

SHOWING 1-10 OF 23 REFERENCES
Constrained Policy Optimization
  • 329
  • PDF
Continuous control with deep reinforcement learning
  • 4,660
  • PDF
Convergent Policy Optimization for Safe Reinforcement Learning
  • 20
  • PDF
End-to-End Training of Deep Visuomotor Policies
  • 2,080
  • PDF
Deep Reinforcement Learning framework for Autonomous Driving
  • 357
  • PDF
A comprehensive survey on safe reinforcement learning
  • 528
  • PDF
...
1
2
3
...