A model-free RL methodology is developed to maximize the probability of LTL satisfaction in unknown stochastic games when the derived DRA has a single Rabin pair, with a generalization providing lower bounds for multiple pairs.
Reinforcement Learning: An Introduction
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2verdicts
UNVERDICTED 2representative citing papers
A model-free RL algorithm uses LTL-derived rewards and path-dependent discounts to learn policies that maximize LTL satisfaction probability with convergence guarantees.
citing papers explorer
-
Model-Free Reinforcement Learning for Stochastic Games with Linear Temporal Logic Objectives
A model-free RL methodology is developed to maximize the probability of LTL satisfaction in unknown stochastic games when the derived DRA has a single Rabin pair, with a generalization providing lower bounds for multiple pairs.
-
Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning
A model-free RL algorithm uses LTL-derived rewards and path-dependent discounts to learn policies that maximize LTL satisfaction probability with convergence guarantees.