Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Goyal, Prasoon"'
Autor:
Dorbala, Vishnu Sashank, Goyal, Prasoon, Piramuthu, Robinson, Johnston, Michael, Manocha, Dinesh, Ghanadhan, Reza
We present and tackle the problem of Embodied Question Answering (EQA) with Situational Queries (S-EQA) in a household environment. Unlike prior EQA work tackling simple queries that directly reference target objects and quantifiable properties perta
Externí odkaz:
http://arxiv.org/abs/2405.04732
Autor:
Mullen Jr, James F., Goyal, Prasoon, Piramuthu, Robinson, Johnston, Michael, Manocha, Dinesh, Ghanadan, Reza
Home robots intend to make their users lives easier. Our work assists in this goal by enabling robots to inform their users of dangerous or unsanitary anomalies in their home. Some examples of these anomalies include the user leaving their milk out,
Externí odkaz:
http://arxiv.org/abs/2404.08827
Autor:
Shi, Hangjie, Ball, Leslie, Thattai, Govind, Zhang, Desheng, Hu, Lucy, Gao, Qiaozi, Shakiah, Suhaila, Gao, Xiaofeng, Padmakumar, Aishwarya, Yang, Bofei, Chung, Cadence, Guthy, Dinakar, Sukhatme, Gaurav, Arumugam, Karthika, Wen, Matthew, Ipek, Osman, Lange, Patrick, Khanna, Rohan, Pansare, Shreyas, Sharma, Vasu, Zhang, Chao, Flagg, Cris, Pressel, Daniel, Vaz, Lavina, Dai, Luke, Goyal, Prasoon, Sahai, Sattvik, Liu, Shaohua, Lu, Yao, Gottardi, Anna, Hu, Shui, Liu, Yang, Hakkani-Tur, Dilek, Bland, Kate, Rocker, Heather, Jeun, James, Rao, Yadunandana, Johnston, Michael, Iyengar, Akshaya, Mandal, Arindam, Natarajan, Prem, Ghanadan, Reza
The Alexa Prize program has empowered numerous university students to explore, experiment, and showcase their talents in building conversational agents through challenges like the SocialBot Grand Challenge and the TaskBot Challenge. As conversational
Externí odkaz:
http://arxiv.org/abs/2308.05221
We introduce a novel setting, wherein an agent needs to learn a task from a demonstration of a related task with the difference between the tasks communicated in natural language. The proposed setting allows reusing demonstrations from other tasks, b
Externí odkaz:
http://arxiv.org/abs/2301.09770
Autor:
Sharma, Vasu, Goyal, Prasoon, Lin, Kaixiang, Thattai, Govind, Gao, Qiaozi, Sukhatme, Gaurav S.
We propose a multimodal (vision-and-language) benchmark for cooperative and heterogeneous multi-agent learning. We introduce a benchmark multimodal dataset with tasks involving collaboration between multiple simulated heterogeneous robots in a rich m
Externí odkaz:
http://arxiv.org/abs/2208.13626
Imitation learning and instruction-following are two common approaches to communicate a user's intent to a learning agent. However, as the complexity of tasks grows, it could be beneficial to use both demonstrations and language to communicate with a
Externí odkaz:
http://arxiv.org/abs/2106.02972
Reinforcement learning (RL), particularly in sparse reward settings, often requires prohibitively large numbers of interactions with the environment, thereby limiting its applicability to complex problems. To address this, several prior approaches ha
Externí odkaz:
http://arxiv.org/abs/2007.15543
Recent reinforcement learning (RL) approaches have shown strong performance in complex domains such as Atari games, but are often highly sample inefficient. A common approach to reduce interaction time with the environment is to use reward shaping, w
Externí odkaz:
http://arxiv.org/abs/1903.02020
The recently developed variational autoencoders (VAEs) have proved to be an effective confluence of the rich representational power of neural networks with Bayesian methods. However, most work on VAEs use a rather simple prior over the latent variabl
Externí odkaz:
http://arxiv.org/abs/1703.07027
Autor:
Bojarski, Mariusz, Del Testa, Davide, Dworakowski, Daniel, Firner, Bernhard, Flepp, Beat, Goyal, Prasoon, Jackel, Lawrence D., Monfort, Mathew, Muller, Urs, Zhang, Jiakai, Zhang, Xin, Zhao, Jake, Zieba, Karol
We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. This end-to-end approach proved surprisingly powerful. With minimum training data from humans the system learns to driv
Externí odkaz:
http://arxiv.org/abs/1604.07316