Zobrazeno 1 - 10
of 315
pro vyhledávání: '"Ushio, Toshimitsu"'
Autor:
Oura, Ryohei, Ushio, Toshimitsu
This letter proposes a learning-based bounded synthesis for a semi-Markov decision process (SMDP) with a linear temporal logic (LTL) specification. In the product of the SMDP and the deterministic $K$-co-B\"uchi automaton (d$K$cBA) converted from the
Externí odkaz:
http://arxiv.org/abs/2204.04383
Publikováno v:
In Neurocomputing 1 December 2024 608
Autor:
Ikemoto, Junya, Ushio, Toshimitsu
Deep reinforcement learning (DRL) has attracted much attention as an approach to solve optimal control problems without mathematical models of systems. On the other hand, in general, constraints may be imposed on optimal control problems. In this stu
Externí odkaz:
http://arxiv.org/abs/2201.08504
Autor:
Ikemoto, Junya, Ushio, Toshimitsu
We apply deep reinforcement learning (DRL) to design of a networked controller with network delays to complete a temporal control task that is described by a signal temporal logic (STL) formula. STL is useful to deal with a specification with a bound
Externí odkaz:
http://arxiv.org/abs/2108.01317
This paper investigates a collaborative rover-copter path planning and exploration with temporal logic specifications under uncertain environments. The objective of the rover is to complete a mission expressed by a syntactically co-safe linear tempor
Externí odkaz:
http://arxiv.org/abs/2107.09303
In this paper, we consider supervisory control of stochastic discrete event systems (SDESs) under linear temporal logic specifications. Applying the bounded synthesis, we reduce the supervisor synthesis into a problem of satisfying a safety condition
Externí odkaz:
http://arxiv.org/abs/2105.03081
To maintain blockchain-based services with ensuring its security, it is an important issue how to decide a mining reward so that the number of miners participating in the mining increases. We propose a dynamical model of decision-making for miners us
Externí odkaz:
http://arxiv.org/abs/2104.08460
Autor:
Ikemoto, Junya, Ushio, Toshimitsu
Applications of reinforcement learning (RL) to stabilization problems of real systems are restricted since an agent needs many experiences to learn an optimal policy and may determine dangerous actions during its exploration. If we know a mathematica
Externí odkaz:
http://arxiv.org/abs/2101.05640
In this paper, we investigate the problem of designing event-triggered controllers for containing epidemic processes in complex networks. We focus on a deterministic susceptible-infected-susceptible (SIS) model, which is one of the well-known, fundam
Externí odkaz:
http://arxiv.org/abs/2012.15146
It is an important decision-making problem for a miner in the blockchain networks if he/she participates in the mining so that he/she earns a reward by creating a new block earlier than other miners. We formulate this decision-making problem as a non
Externí odkaz:
http://arxiv.org/abs/2010.05370