Lyapunov-based Safe Policy Optimization for Continuous Control

Yinlam Chow
Yinlam Chow
Edgar A. Duéñez-Guzmán
Edgar A. Duéñez-Guzmán

arXiv: Learning, 2019.

Cited by: 0|Bibtex|Views28
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

We study continuous action reinforcement learning problems in which it is crucial that the agent interacts with the environment only through {em safe} policies, i.e.,~policies that do not take the agent to undesirable situations. We formulate these problems as {em constrained} Markov decision processes (CMDPs) and present safe policy opti...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments