Zobrazeno 1 - 10
of 305
pro vyhledávání: '"Peng, Xiangyu"'
Post-training Large Language Models (LLMs) with explicit reasoning trajectories can enhance their reasoning abilities. However, acquiring such high-quality trajectory data typically demands meticulous supervision from humans or superior models, which
Externí odkaz:
http://arxiv.org/abs/2410.02108
With the advance of deep learning, much progress has been made in building powerful artificial intelligence (AI) systems for automatic Chest X-ray (CXR) analysis. Most existing AI models are trained to be a binary classifier with the aim of distingui
Externí odkaz:
http://arxiv.org/abs/2408.02214
Wearable robotic systems are a class of robots that have a tight coupling between human and robot movements. Similar to non-wearable robots, it is important to measure the trust a person has that the robot can support achieving the desired goals. Whi
Externí odkaz:
http://arxiv.org/abs/2407.07200
Autor:
Jin, Claire, Rao, Sudha, Peng, Xiangyu, Botchway, Portia, Quaye, Jessica, Brockett, Chris, Dolan, Bill
Advancements in large language models (LLMs) are revolutionizing interactive game design, enabling dynamic plotlines and interactions between players and non-player characters (NPCs). However, LLMs may exhibit flaws such as hallucinations, forgetfuln
Externí odkaz:
http://arxiv.org/abs/2406.04482
Open-ended worlds are those in which there are no pre-specified goals or environmental reward signal. As a consequence, an agent must know how to perform a multitude of tasks. However, when a new task is presented to an agent, we expect it to be able
Externí odkaz:
http://arxiv.org/abs/2405.06059
Autor:
Peng, Xiangyu, Quaye, Jessica, Rao, Sudha, Xu, Weijia, Botchway, Portia, Brockett, Chris, Jojic, Nebojsa, DesGarennes, Gabriel, Lobb, Ken, Xu, Michael, Leandro, Jorge, Jin, Claire, Dolan, Bill
Publikováno v:
IEEE Conference on Games 2024
We explore how interaction with large language models (LLMs) can give rise to emergent behaviors, empowering players to participate in the evolution of game narratives. Our testbed is a text-adventure game in which players attempt to solve a mystery
Externí odkaz:
http://arxiv.org/abs/2404.17027
Autor:
Zhou, Daquan, Wang, Kai, Gu, Jianyang, Peng, Xiangyu, Lian, Dongze, Zhang, Yifan, You, Yang, Feng, Jiashi
State-of-the-art deep neural networks are trained with large amounts (millions or even billions) of data. The expensive computation and memory costs make it difficult to train them on limited hardware resources, especially for recent popular large la
Externí odkaz:
http://arxiv.org/abs/2308.10524
Text-adventure games and text role-playing games are grand challenges for reinforcement learning game playing agents. Text role-playing games are open-ended environments where an agent must faithfully play a particular character. We consider the dist
Externí odkaz:
http://arxiv.org/abs/2308.01872
Imaginative play is an area of creativity that could allow robots to engage with the world around them in a much more personified way. Imaginary play can be seen as taking real objects and locations and using them as imaginary objects and locations i
Externí odkaz:
http://arxiv.org/abs/2308.01734
One major challenge in reinforcement learning (RL) is the large amount of steps for the RL agent needs to converge in the training process and learn the optimal policy, especially in text-based game environments where the action space is extensive. H
Externí odkaz:
http://arxiv.org/abs/2307.15833