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.
Rabinizer 4: from LTL to your favourite deterministic automaton
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2020 1verdicts
UNVERDICTED 1representative citing papers
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.