Zobrazeno 1 - 10
of 155
pro vyhledávání: '"Zhan, Wenhao"'
Autor:
Huang, Audrey, Zhan, Wenhao, Xie, Tengyang, Lee, Jason D., Sun, Wen, Krishnamurthy, Akshay, Foster, Dylan J.
Language model alignment methods, such as reinforcement learning from human feedback (RLHF), have led to impressive advances in language model capabilities, but existing techniques are limited by a widely observed phenomenon known as overoptimization
Externí odkaz:
http://arxiv.org/abs/2407.13399
Autor:
Gao, Zhaolin, Chang, Jonathan D., Zhan, Wenhao, Oertell, Owen, Swamy, Gokul, Brantley, Kianté, Joachims, Thorsten, Bagnell, J. Andrew, Lee, Jason D., Sun, Wen
While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications, including the fine-tuning of generative models. Unfortunately, PPO
Externí odkaz:
http://arxiv.org/abs/2404.16767
Autor:
Chang, Jonathan D., Zhan, Wenhao, Oertell, Owen, Brantley, Kianté, Misra, Dipendra, Lee, Jason D., Sun, Wen
Reinforcement Learning (RL) from Human Preference-based feedback is a popular paradigm for fine-tuning generative models, which has produced impressive models such as GPT-4 and Claude3 Opus. This framework often consists of two steps: learning a rewa
Externí odkaz:
http://arxiv.org/abs/2404.08495
Multi-distribution learning (MDL), which seeks to learn a shared model that minimizes the worst-case risk across $k$ distinct data distributions, has emerged as a unified framework in response to the evolving demand for robustness, fairness, multi-gr
Externí odkaz:
http://arxiv.org/abs/2312.05134
Autor:
Zhao, Yulai, Zhan, Wenhao, Hu, Xiaoyan, Leung, Ho-fung, Farnia, Farzan, Sun, Wen, Lee, Jason D.
We study risk-sensitive Reinforcement Learning (RL), where we aim to maximize the Conditional Value at Risk (CVaR) with a fixed risk tolerance $\tau$. Prior theoretical work studying risk-sensitive RL focuses on the tabular Markov Decision Processes
Externí odkaz:
http://arxiv.org/abs/2311.11965
Preference-based Reinforcement Learning (PbRL) is a paradigm in which an RL agent learns to optimize a task using pair-wise preference-based feedback over trajectories, rather than explicit reward signals. While PbRL has demonstrated practical succes
Externí odkaz:
http://arxiv.org/abs/2305.18505
In this paper, we investigate the problem of offline Preference-based Reinforcement Learning (PbRL) with human feedback where feedback is available in the form of preference between trajectory pairs rather than explicit rewards. Our proposed algorith
Externí odkaz:
http://arxiv.org/abs/2305.14816
This paper studies tabular reinforcement learning (RL) in the hybrid setting, which assumes access to both an offline dataset and online interactions with the unknown environment. A central question boils down to how to efficiently utilize online dat
Externí odkaz:
http://arxiv.org/abs/2305.10282
Autor:
Jin, Jun1 (AUTHOR), Zhan, Wenhao1 (AUTHOR), Li, Haisheng2 (AUTHOR), Ding, Yi1 (AUTHOR), Li, Jie1,3,4 (AUTHOR) lijiebwu@163.com
Publikováno v:
Mathematics (2227-7390). Aug2024, Vol. 12 Issue 15, p2431. 24p.
In this paper we study online Reinforcement Learning (RL) in partially observable dynamical systems. We focus on the Predictive State Representations (PSRs) model, which is an expressive model that captures other well-known models such as Partially O
Externí odkaz:
http://arxiv.org/abs/2207.05738