Zobrazeno 1 - 10
of 10 968
pro vyhledávání: '"A, Topcu"'
Autor:
Amini, Arash, Bayiz, Yigit Ege, Lee, Eun-Ju, Somer-Topcu, Zeynep, Marculescu, Radu, Topcu, Ufuk
Competition among news sources may encourage some sources to share fake news and misinformation to influence the public. While sharing misinformation may lead to a short-term gain in audience engagement, it may damage the reputation of these sources,
Externí odkaz:
http://arxiv.org/abs/2411.15677
We develop compositional learning algorithms for coupled dynamical systems. While deep learning has proven effective at modeling complex relationships from data, compositional couplings between system components typically introduce algebraic constrai
Externí odkaz:
http://arxiv.org/abs/2412.11215
Autor:
Koprulu, Cevahir, Li, Po-han, Qiu, Tianyu, Zhao, Ruihan, Westenbroek, Tyler, Fridovich-Keil, David, Chinchali, Sandeep, Topcu, Ufuk
Many continuous control problems can be formulated as sparse-reward reinforcement learning (RL) tasks. In principle, online RL methods can automatically explore the state space to solve each new task. However, discovering sequences of actions that le
Externí odkaz:
http://arxiv.org/abs/2412.01114
Autonomous agents perceive and interpret their surroundings by integrating multimodal inputs, such as vision, audio, and LiDAR. These perceptual modalities support retrieval tasks, such as place recognition in robotics. However, current multimodal re
Externí odkaz:
http://arxiv.org/abs/2411.10513
Multimodal foundation models offer a promising framework for robotic perception and planning by processing sensory inputs to generate actionable plans. However, addressing uncertainty in both perception (sensory interpretation) and decision-making (p
Externí odkaz:
http://arxiv.org/abs/2411.01639
Strategic coordination between autonomous agents and human partners under incomplete information can be modeled as turn-based cooperative games. We extend a turn-based game under incomplete information, the shared-control game, to allow players to ta
Externí odkaz:
http://arxiv.org/abs/2410.18242
Autor:
Liu, Xinjie, Li, Jingqi, Fotiadis, Filippos, Karabag, Mustafa O., Milzman, Jesse, Fridovich-Keil, David, Topcu, Ufuk
Common feedback strategies in multi-agent dynamic games require all players' state information to compute control strategies. However, in real-world scenarios, sensing and communication limitations between agents make full state feedback expensive or
Externí odkaz:
http://arxiv.org/abs/2410.16441
We develop a method that integrates the tree of thoughts and multi-agent framework to enhance the capability of pre-trained language models in solving complex, unfamiliar games. The method decomposes game-solving into four incremental tasks -- game s
Externí odkaz:
http://arxiv.org/abs/2410.14890
Although pre-trained language models can generate executable plans (e.g., programmatic policies) for solving robot tasks, the generated plans may violate task-relevant logical specifications due to the models' black-box nature. A significant gap rema
Externí odkaz:
http://arxiv.org/abs/2410.14865
Multimodal encoders like CLIP excel in tasks such as zero-shot image classification and cross-modal retrieval. However, they require excessive training data. We propose canonical similarity analysis (CSA), which uses two unimodal encoders to replicat
Externí odkaz:
http://arxiv.org/abs/2410.07610