Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Keren, Sarah"'
The rapidly changing architecture and functionality of electrical networks and the increasing penetration of renewable and distributed energy resources have resulted in various technological and managerial challenges. These have rendered traditional
Externí odkaz:
http://arxiv.org/abs/2404.15583
One of the most difficult challenges in creating successful human-AI collaborations is aligning a robot's behavior with a human user's expectations. When this fails to occur, a robot may misinterpret their specified goals, prompting it to perform act
Externí odkaz:
http://arxiv.org/abs/2404.15184
Goal recognition design aims to make limited modifications to decision-making environments with the goal of making it easier to infer the goals of agents acting within those environments. Although various research efforts have been made in goal recog
Externí odkaz:
http://arxiv.org/abs/2404.03054
Publikováno v:
Advances in Neural Information Processing Systems, 36 (2023)
We present a novel multi-agent RL approach, Selective Multi-Agent Prioritized Experience Relay, in which agents share with other agents a limited number of transitions they observe during training. The intuition behind this is that even a small numbe
Externí odkaz:
http://arxiv.org/abs/2311.00865
In multiple realistic settings, a robot is tasked with grasping an object without knowing its exact pose and relies on a probabilistic estimation of the pose to decide how to attempt the grasp. We support settings in which it is possible to provide t
Externí odkaz:
http://arxiv.org/abs/2310.14402
Mobile robotic agents often suffer from localization uncertainty which grows with time and with the agents' movement. This can hinder their ability to accomplish their task. In some settings, it may be possible to perform assistive actions that reduc
Externí odkaz:
http://arxiv.org/abs/2308.11961
Recent studies show that deep reinforcement learning (DRL) agents tend to overfit to the task on which they were trained and fail to adapt to minor environment changes. To expedite learning when transferring to unseen tasks, we propose a novel approa
Externí odkaz:
http://arxiv.org/abs/2307.05209
Autor:
Finkelstein, Mira, Liu, Lucy, Schlot, Nitsan Levy, Kolumbus, Yoav, Parkes, David C., Rosenshein, Jeffrey S., Keren, Sarah
Understanding emerging behaviors of reinforcement learning (RL) agents may be difficult since such agents are often trained in complex environments using highly complex decision making procedures. This has given rise to a variety of approaches to exp
Externí odkaz:
http://arxiv.org/abs/2209.12006
AI agents need to be robust to unexpected changes in their environment in order to safely operate in real-world scenarios. While some work has been done on this type of robustness in the single-agent case, in this work we introduce the idea that coll
Externí odkaz:
http://arxiv.org/abs/2111.06614
Autor:
Kulkarni, Anagha, Sreedharan, Sarath, Keren, Sarah, Chakraborti, Tathagata, Smith, David, Kambhampati, Subbarao
Designing robots capable of generating interpretable behavior is a prerequisite for achieving effective human-robot collaboration. This means that the robots need to be capable of generating behavior that aligns with human expectations and, when requ
Externí odkaz:
http://arxiv.org/abs/2007.00820