Zobrazeno 1 - 10
of 158
pro vyhledávání: '"Bölöni, Ladislau"'
Autor:
Almohaimeed, Saad, Almohaimeed, Saleh, Shafin, Ashfaq Ali, Carbunar, Bogdan, Bölöni, Ladislau
Detecting harmful content on social media, such as Twitter, is made difficult by the fact that the seemingly simple yes/no classification conceals a significant amount of complexity. Unfortunately, while several datasets have been collected for train
Externí odkaz:
http://arxiv.org/abs/2311.06446
Autor:
Matloob, Samuel, Datta, Partha P., Kreidl, O. Patrick, Dutta, Ayan, Roy, Swapnoneel, Bölöni, Ladislau
Recent developments in robotic and sensor hardware make data collection with mobile robots (ground or aerial) feasible and affordable to a wide population of users. The newly emergent applications, such as precision agriculture, weather damage assess
Externí odkaz:
http://arxiv.org/abs/2305.06243
Throughout the Covid-19 pandemic, a significant amount of effort had been put into developing techniques that predict the number of infections under various assumptions about the public policy and non-pharmaceutical interventions. While both the avai
Externí odkaz:
http://arxiv.org/abs/2112.11187
The daily activities performed by a disabled or elderly person can be monitored by a smart environment, and the acquired data can be used to learn a predictive model of user behavior. To speed up the learning, several researchers designed collaborati
Externí odkaz:
http://arxiv.org/abs/2101.06564
Autor:
Sheikh, Hassam Ullah, Bölöni, Ladislau
The classic DQN algorithm is limited by the overestimation bias of the learned Q-function. Subsequent algorithms have proposed techniques to reduce this problem, without fully eliminating it. Recently, the Maxmin and Ensemble Q-learning algorithms ha
Externí odkaz:
http://arxiv.org/abs/2006.13823
Autor:
Khodadadeh, Siavash, Zehtabian, Sharare, Vahidian, Saeed, Wang, Weijia, Lin, Bill, Bölöni, Ladislau
Unsupervised meta-learning approaches rely on synthetic meta-tasks that are created using techniques such as random selection, clustering and/or augmentation. Unfortunately, clustering and augmentation are domain-dependent, and thus they require eith
Externí odkaz:
http://arxiv.org/abs/2006.10236
Autor:
Sheikh, Hassam Ullah, Bölöni, Ladislau
Many cooperative multi-agent problems require agents to learn individual tasks while contributing to the collective success of the group. This is a challenging task for current state-of-the-art multi-agent reinforcement algorithms that are designed t
Externí odkaz:
http://arxiv.org/abs/2003.10598
Autor:
Abolghasemi, Pooya, Bölöni, Ladislau
Recent research demonstrated that it is feasible to end-to-end train multi-task deep visuomotor policies for robotic manipulation using variations of learning from demonstration (LfD) and reinforcement learning (RL). In this paper, we extend the capa
Externí odkaz:
http://arxiv.org/abs/1909.11128
Autor:
Sheikh, Hassam Ullah, Bölöni, Ladislau
We explore a collaborative and cooperative multi-agent reinforcement learning setting where a team of reinforcement learning agents attempt to solve a single cooperative task in a multi-scenario setting. We propose a novel multi-agent reinforcement l
Externí odkaz:
http://arxiv.org/abs/1908.09184
Autor:
Sheikh, Hassam Ullah, Bölöni, Ladislau
We are considering a scenario where a team of bodyguard robots provides physical protection to a VIP in a crowded public space. We use deep reinforcement learning to learn the policy to be followed by the robots. As the robot bodyguards need to follo
Externí odkaz:
http://arxiv.org/abs/1901.09837