Zobrazeno 1 - 10
of 83
pro vyhledávání: '"Hu, Shengchao"'
Offline reinforcement learning (RL) methods harness previous experiences to derive an optimal policy, forming the foundation for pre-trained large-scale models (PLMs). When encountering tasks not seen before, PLMs often utilize several expert traject
Externí odkaz:
http://arxiv.org/abs/2411.01168
The purpose of offline multi-task reinforcement learning (MTRL) is to develop a unified policy applicable to diverse tasks without the need for online environmental interaction. Recent advancements approach this through sequence modeling, leveraging
Externí odkaz:
http://arxiv.org/abs/2411.01146
In numerous artificial intelligence applications, the collaborative efforts of multiple intelligent agents are imperative for the successful attainment of target objectives. To enhance coordination among these agents, a distributed communication fram
Externí odkaz:
http://arxiv.org/abs/2411.00382
Autor:
Hu, Jifeng, Huang, Sili, Shen, Li, Yang, Zhejian, Hu, Shengchao, Tang, Shisong, Chen, Hechang, Chang, Yi, Tao, Dacheng, Sun, Lichao
Continual offline reinforcement learning (CORL) has shown impressive ability in diffusion-based lifelong learning systems by modeling the joint distributions of trajectories. However, most research only focuses on limited continual task settings wher
Externí odkaz:
http://arxiv.org/abs/2410.15698
Structured pruning is a promising hardware-friendly compression technique for large language models (LLMs), which is expected to be retraining-free to avoid the enormous retraining cost. This retraining-free paradigm involves (1) pruning criteria to
Externí odkaz:
http://arxiv.org/abs/2407.13331
Autor:
Fan, Ziqing, Hu, Shengchao, Yao, Jiangchao, Niu, Gang, Zhang, Ya, Sugiyama, Masashi, Wang, Yanfeng
In federated learning (FL), the multi-step update and data heterogeneity among clients often lead to a loss landscape with sharper minima, degenerating the performance of the resulted global model. Prevalent federated approaches incorporate sharpness
Externí odkaz:
http://arxiv.org/abs/2405.18890
The purpose of offline multi-task reinforcement learning (MTRL) is to develop a unified policy applicable to diverse tasks without the need for online environmental interaction. Recent advancements approach this through sequence modeling, leveraging
Externí odkaz:
http://arxiv.org/abs/2405.18080
Recent advancements in offline reinforcement learning (RL) have underscored the capabilities of Conditional Sequence Modeling (CSM), a paradigm that learns the action distribution based on history trajectory and target returns for each state. However
Externí odkaz:
http://arxiv.org/abs/2405.17098
Autor:
Dai, Yang, Ma, Oubo, Zhang, Longfei, Liang, Xingxing, Hu, Shengchao, Wang, Mengzhu, Ji, Shouling, Huang, Jincai, Shen, Li
Transformer-based trajectory optimization methods have demonstrated exceptional performance in offline Reinforcement Learning (offline RL). Yet, it poses challenges due to substantial parameter size and limited scalability, which is particularly crit
Externí odkaz:
http://arxiv.org/abs/2405.12094
In numerous artificial intelligence applications, the collaborative efforts of multiple intelligent agents are imperative for the successful attainment of target objectives. To enhance coordination among these agents, a distributed communication fram
Externí odkaz:
http://arxiv.org/abs/2405.08550