Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Hafez, Muhammad Burhan"'
Inspired by the success of the Transformer architecture in natural language processing and computer vision, we investigate the use of Transformers in Reinforcement Learning (RL), specifically in modeling the environment's dynamics using Transformer D
Externí odkaz:
http://arxiv.org/abs/2407.18841
Endowing robots with the human ability to learn a growing set of skills over the course of a lifetime as opposed to mastering single tasks is an open problem in robot learning. While multi-task learning approaches have been proposed to address this p
Externí odkaz:
http://arxiv.org/abs/2309.04974
Publikováno v:
Frontiers in Neurorobotics 17:1127642 (2023)
Deep Reinforcement Learning agents often suffer from catastrophic forgetting, forgetting previously found solutions in parts of the input space when training on new data. Replay Memories are a common solution to the problem, decorrelating and shuffli
Externí odkaz:
http://arxiv.org/abs/2305.02054
Over the last few years, we have not seen any major developments in model-free or model-based learning methods that would make one obsolete relative to the other. In most cases, the used technique is heavily dependent on the use case scenario or othe
Externí odkaz:
http://arxiv.org/abs/2304.07219
Programming robot behavior in a complex world faces challenges on multiple levels, from dextrous low-level skills to high-level planning and reasoning. Recent pre-trained Large Language Models (LLMs) have shown remarkable reasoning ability in few-sho
Externí odkaz:
http://arxiv.org/abs/2303.08268
Autor:
Özdemir, Ozan, Kerzel, Matthias, Weber, Cornelius, Lee, Jae Hee, Hafez, Muhammad Burhan, Bruns, Patrick, Wermter, Stefan
Publikováno v:
Applied Artificial Intelligence Volume 37, 2023 - Issue 1
Human infant learning happens during exploration of the environment, by interaction with objects, and by listening to and repeating utterances casually, which is analogous to unsupervised learning. Only occasionally, a learning infant would receive a
Externí odkaz:
http://arxiv.org/abs/2301.03353
Sound is one of the most informative and abundant modalities in the real world while being robust to sense without contacts by small and cheap sensors that can be placed on mobile devices. Although deep learning is capable of extracting information f
Externí odkaz:
http://arxiv.org/abs/2208.02680
Recent advances in robot learning have enabled robots to become increasingly better at mastering a predefined set of tasks. On the other hand, as humans, we have the ability to learn a growing set of tasks over our lifetime. Continual robot learning
Externí odkaz:
http://arxiv.org/abs/2107.04533
Publikováno v:
Proc. Intl. Joint Conf. Neural Networks (IJCNN), 2021, forthcoming
Using a model of the environment, reinforcement learning agents can plan their future moves and achieve superhuman performance in board games like Chess, Shogi, and Go, while remaining relatively sample-efficient. As demonstrated by the MuZero Algori
Externí odkaz:
http://arxiv.org/abs/2102.05599
Publikováno v:
Robotics and Autonomous Systems 133 (2020) 103630
Combining model-based and model-free learning systems has been shown to improve the sample efficiency of learning to perform complex robotic tasks. However, dual-system approaches fail to consider the reliability of the learned model when it is appli
Externí odkaz:
http://arxiv.org/abs/2004.08830