STL is a rich logic that can be used to describe tasks involving bounds on physical parameters, continuous time bounds, and logical relationships over time and ...
Poster: Enforcing temporal logic specifications via reinforcement learning. Austin Jones, Derya Aksaray, Zhaodan Kong, Mac Schwager, Calin Belta. Research ...
Apr 6, 2024 · We consider the problem of controlling a system with unknown, stochastic dynamics to achieve a complex, time-sensitive task.
In this paper, we use formal specification languages to capture the designer's requirements of what the robot should achieve. We propose Truncated Linear ...
Missing: via | Show results with:via
This paper studies the problem of synthesizing control policies for uncertain continuous-time nonlinear systems from linear temporal logic (LTL) ...
In this paper, we presented a new reinforcement learning paradigm to enforce temporal logic specifications when the dynamics of the system are a priori ...
Feb 2, 2023 · This paper proposes an advanced Reinforcement Learning (RL) method, incorporating reward-shaping, safety value functions, and a quantum ...
Nov 30, 2022 · In this paper, leveraging the concept of funnel functions, we propose a tractable reinforcement learning algorithm to learn a time-dependent ...
The goal of this paper is to combine the best of two worlds, namely (1) the formal correctness guarantees of a controller. w.r.t. a temporal logic specification ...
We demonstrate via a pair of robot navigation simulation case studies that reinforcement learning with robustness maximization performs better than probability ...