Sign in

Formal Controller Synthesis for Continuous-Space MDPs via Model-Free Reinforcement Learning

By Abolfazl Lavaei and others
A novel reinforcement learning scheme to synthesize policies for continuous-space Markov decision processes (MDPs) is proposed. This scheme enables one to apply model-free, off-the-shelf reinforcement learning algorithms for finite MDPs to compute optimal strategies for the corresponding continuous-space MDPs without explicitly constructing the finite-state abstraction. The proposed approach is based... Show more
March 2, 2020
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
Formal Controller Synthesis for Continuous-Space MDPs via Model-Free Reinforcement Learning
Click on play to start listening