The need for computationally-efficient control methods of dynamical systems under temporal logic tasks has recently become more apparent. Existing methods are computationally …
In control theory, complex models of physical processes, such as systems of differential or difference equations, are usually checked against simple specifications, such as stability …
X Yin, B Gao, X Yu - Annual Reviews in Control, 2024 - Elsevier
In recent years, formal methods have been extensively used in the design of autonomous systems. By employing mathematically rigorous techniques, formal methods can provide …
Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains …
We study the problem of learning control policies for complex tasks given by logical specifications. Recent approaches automatically generate a reward function from a given …
X Li, CI Vasile, C Belta - 2017 IEEE/RSJ International …, 2017 - ieeexplore.ieee.org
Reinforcement learning (RL) depends critically on the choice of reward functions used to capture the desired behavior and constraints of a robot. Usually, these are handcrafted by a …
We present a reinforcement learning (RL) frame-work to synthesize a control policy from a given linear temporal logic (LTL) specification in an unknown stochastic environment that …
This letter investigates the motion planning of autonomous dynamical systems modeled by Markov decision processes (MDP) with unknown transition probabilities over continuous …
We address the problem of teaching a deep reinforcement learning (RL) agent to follow instructions in multi-task environments. Instructions are expressed in a well-known formal …