69 citations · 151 across the 30 of their papers we have counts for
10 papers · 1 filter
The Effects of Data Augmentation on Confidence Estimation for LLMs
Rui Wang, Renyu Zhu, Minmin Lin +4
Confidence estimation is crucial for reflecting the reliability of large language models (LLMs), particularly in the widely used closed-source models. Utilizing data augmentation f…
Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards
Zhaohui Jiang, Xuening Feng, Paul Weng +6
In practice, reinforcement learning (RL) agents are often trained with a possibly imperfect proxy reward function, which may lead to a human-agent alignment issue (i.e., the learne…
Bayesian Design Principles for Offline-to-Online Reinforcement Learning
Hao Hu, Yiqin Yang, Jianing Ye +7
Offline reinforcement learning (RL) is crucial for real-world applications where exploration can be costly or unsafe. However, offline learned policies are often suboptimal, and fu…
vMFER: Von Mises-Fisher Experience Resampling Based on Uncertainty of Gradient Directions for Policy Improvement
Yiwen Zhu, Jinyi Liu, Wenya Wei +7
Reinforcement Learning (RL) is a widely employed technique in decision-making problems, encompassing two fundamental operations -- policy evaluation and policy improvement. Enhanci…
Examining the Effect of Pre-training on Time Series Classification
Jiashu Pu, Shiwei Zhao, Ling Cheng +4
Although the pre-training followed by fine-tuning paradigm is used extensively in many fields, there is still some controversy surrounding the impact of pre-training on the fine-tu…
Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type Perspective
Renyu Zhu, Haoyu Liu, Runze Wu +4
In this paper, we investigate the problem of learning with noisy labels in real-world annotation scenarios, where noise can be categorized into two types: factual noise and ambigui…
Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning
Jinyi Liu, Yi Ma, Jianye Hao +4
In recent years, data-driven reinforcement learning (RL), also known as offline RL, have gained significant attention. However, the role of data sampling techniques in offline RL h…
TCFimt: Temporal Counterfactual Forecasting from Individual Multiple Treatment Perspective
Pengfei Xi, Guifeng Wang, Zhipeng Hu +8
Determining causal effects of temporal multi-intervention assists decision-making. Restricted by time-varying bias, selection bias, and interactions of multiple interventions, the…
Reinforcement Learning Experience Reuse with Policy Residual Representation
Wen-Ji Zhou, Yang Yu, Yingfeng Chen +4
Experience reuse is key to sample-efficient reinforcement learning. One of the critical issues is how the experience is represented and stored. Previously, the experience can be st…
Hierarchical Deep Multiagent Reinforcement Learning with Temporal Abstraction
Hongyao Tang, Jianye Hao, Tangjie Lv +8
Multiagent reinforcement learning (MARL) is commonly considered to suffer from non-stationary environments and exponentially increasing policy space. It would be even more challeng…