Sign in

Compositional Reinforcement Learning for Discrete-Time Stochastic Control Systems

By Abolfazl Lavaei and others
We propose a compositional approach to synthesize policies for networks of continuous-space stochastic control systems with unknown dynamics using model-free reinforcement learning (RL). The approach is based on implicitly abstracting each subsystem in the network with a finite Markov decision process with unknown transition probabilities, synthesizing a strategy for each... Show more
August 6, 2022
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
Compositional Reinforcement Learning for Discrete-Time Stochastic Control Systems
Click on play to start listening