A model-free RL algorithm uses LTL-derived rewards and path-dependent discounts to learn policies that maximize LTL satisfaction probability with convergence guarantees.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.