Zobrazeno 1 - 10
of 55
pro vyhledávání: '"Yang, Tianpei"'
This paper introduces the problem of learning to place logic blocks in Field-Programmable Gate Arrays (FPGAs) and a learning-based method. In contrast to previous search-based placement algorithms, we instead employ Reinforcement Learning (RL) with t
Externí odkaz:
http://arxiv.org/abs/2404.13061
Fine-tuning Large Language Models (LLMs) adapts a trained model to specific downstream tasks, significantly improving task-specific performance. Supervised Fine-Tuning (SFT) is a common approach, where an LLM is trained to produce desired answers. Ho
Externí odkaz:
http://arxiv.org/abs/2401.00907
Autor:
Rasouli, Amir, Goebel, Randy, Taylor, Matthew E., Kotseruba, Iuliia, Alizadeh, Soheil, Yang, Tianpei, Alban, Montgomery, Shkurti, Florian, Zhuang, Yuzheng, Scibior, Adam, Rezaee, Kasra, Garg, Animesh, Meger, David, Luo, Jun, Paull, Liam, Zhang, Weinan, Wang, Xinyu, Chen, Xi
Driving SMARTS is a regular competition designed to tackle problems caused by the distribution shift in dynamic interaction contexts that are prevalent in real-world autonomous driving (AD). The proposed competition supports methodologically diverse
Externí odkaz:
http://arxiv.org/abs/2211.07545
Autor:
Jafferjee, Taher, Ziomek, Juliusz, Yang, Tianpei, Dai, Zipeng, Wang, Jianhong, Taylor, Matthew, Shao, Kun, Wang, Jun, Mguni, David
Centralised training with decentralised execution (CT-DE) serves as the foundation of many leading multi-agent reinforcement learning (MARL) algorithms. Despite its popularity, it suffers from a critical drawback due to its reliance on learning from
Externí odkaz:
http://arxiv.org/abs/2209.01054
Autor:
Cao, Yushi, Li, Zhiming, Yang, Tianpei, Zhang, Hao, Zheng, Yan, Li, Yi, Hao, Jianye, Liu, Yang
Despite achieving superior performance in human-level control problems, unlike humans, deep reinforcement learning (DRL) lacks high-order intelligence (e.g., logic deduction and reuse), thus it behaves ineffectively than humans regarding learning and
Externí odkaz:
http://arxiv.org/abs/2205.13728
PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration
Autor:
Li, Pengyi, Tang, Hongyao, Yang, Tianpei, Hao, Xiaotian, Sang, Tong, Zheng, Yan, Hao, Jianye, Taylor, Matthew E., Tao, Wenyuan, Wang, Zhen, Barez, Fazl
Learning to collaborate is critical in Multi-Agent Reinforcement Learning (MARL). Previous works promote collaboration by maximizing the correlation of agents' behaviors, which is typically characterized by Mutual Information (MI) in different forms.
Externí odkaz:
http://arxiv.org/abs/2203.08553
Autor:
Glanois, Claire, Weng, Paul, Zimmer, Matthieu, Li, Dong, Yang, Tianpei, Hao, Jianye, Liu, Wulong
Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains such as autonomous driving or medical applications. In such contexts,
Externí odkaz:
http://arxiv.org/abs/2112.13112
Autor:
Hao, Jianye, Yang, Tianpei, Tang, Hongyao, Bai, Chenjia, Liu, Jinyi, Meng, Zhaopeng, Liu, Peng, Wang, Zhen
Deep Reinforcement Learning (DRL) and Deep Multi-agent Reinforcement Learning (MARL) have achieved significant successes across a wide range of domains, including game AI, autonomous vehicles, robotics, and so on. However, DRL and deep MARL agents ar
Externí odkaz:
http://arxiv.org/abs/2109.06668
Autor:
Mguni, David, Jafferjee, Taher, Wang, Jianhong, Perez-Nieves, Nicolas, Yang, Tianpei, Taylor, Matthew, Song, Wenbin, Tong, Feifei, Chen, Hui, Zhu, Jiangcheng, Wang, Jun, Yang, Yaodong
Reward shaping (RS) is a powerful method in reinforcement learning (RL) for overcoming the problem of sparse or uninformative rewards. However, RS typically relies on manually engineered shaping-reward functions whose construction is time-consuming a
Externí odkaz:
http://arxiv.org/abs/2103.09159
Autor:
Yang, Tianpei, Hao, Jianye, Meng, Zhaopeng, Zhang, Zongzhang, Hu, Yujing, Cheng, Yingfeng, Fan, Changjie, Wang, Weixun, Liu, Wulong, Wang, Zhaodong, Peng, Jiajie
Transfer Learning (TL) has shown great potential to accelerate Reinforcement Learning (RL) by leveraging prior knowledge from past learned policies of relevant tasks. Existing transfer approaches either explicitly computes the similarity between task
Externí odkaz:
http://arxiv.org/abs/2002.08037