62 citations · 115 across the 13 of their papers we have counts for
13 papers · 1 filter
Provably Efficient Risk-Sensitive Offline Reinforcement Learning via Optimized Certainty Equivalents
Hanzhen Wang, Boxiang Lyu, Zhongxiang Dai +3
Risk-sensitive reinforcement learning (RL) addresses decision-making under uncertainty and adverse outcomes. Learning risk-sensitive policies from fixed datasets is important when…
Unifying Value Alignment and Assignment in Cross-Domain Offline Reinforcement Learning with Heterogeneous Datasets
Zhongjian Qiao, Jiafei Lyu, Chenjia Bai +3
Cross-domain offline reinforcement learning (RL) aims to learn a policy in the target domain with a limited target domain dataset and a source domain dataset that exhibits a dynami…
Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting
Zhongjian Qiao, Jiafei Lyu, Boxiang Lyu +3
Model-based offline reinforcement learning (RL) aims to enhance offline RL with a dynamics model that facilitates policy exploration. However, \textit{model exploitation} could occ…
Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts
Zhongjian Qiao, Rui Yang, Jiafei Lyu +5
Single-domain offline reinforcement learning (RL) often suffers from limited data coverage, while cross-domain offline RL handles this issue by leveraging additional data from othe…
Efficient Cross-Domain Offline Reinforcement Learning with Dynamics- and Value-Aligned Data Filtering
Zhongjian Qiao, Rui Yang, Jiafei Lyu +4
Cross-domain offline reinforcement learning (RL) aims to train a well-performing agent in the target environment, leveraging both a limited target domain dataset and a source domai…
Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
Yiran Guo, Lijie Xu, Jie Liu +2
Enhancing the reasoning capabilities of large language models effectively using reinforcement learning (RL) remains a crucial challenge. Existing approaches primarily adopt two con…
Online Preference Alignment for Language Models via Count-based Exploration
Chenjia Bai, Yang Zhang, Shuang Qiu +3
Reinforcement Learning from Human Feedback (RLHF) has shown great potential in fine-tuning Large Language Models (LLMs) to align with human preferences. Existing methods perform pr…
Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards
Haoxiang Wang, Yong Lin, Wei Xiong +5
Fine-grained control over large language models (LLMs) remains a significant challenge, hindering their adaptability to diverse user needs. While Reinforcement Learning from Human…
Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
Rui Yang, Xiaoman Pan, Feng Luo +4
We consider the problem of multi-objective alignment of foundation models with human preferences, which is a critical step towards helpful and harmless AI systems. However, it is g…
Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning
Shuang Qiu, Lingxiao Wang, Chenjia Bai +2
In view of its power in extracting feature representation, contrastive self-supervised learning has been successfully integrated into the practice of (deep) reinforcement learning…
Single-Timescale Stochastic Nonconvex-Concave Optimization for Smooth Nonlinear TD Learning
Shuang Qiu, Zhuoran Yang, Xiaohan Wei +2
Temporal-Difference (TD) learning with nonlinear smooth function approximation for policy evaluation has achieved great success in modern reinforcement learning. It is shown that s…
Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss
Shuang Qiu, Xiaohan Wei, Zhuoran Yang +2
We consider online learning for episodic stochastically constrained Markov decision processes (CMDPs), which plays a central role in ensuring the safety of reinforcement learning.…
Central Server Free Federated Learning over Single-sided Trust Social Networks
Chaoyang He, Conghui Tan, Hanlin Tang +2
Federated learning has become increasingly important for modern machine learning, especially for data privacy-sensitive scenarios. Existing federated learning mostly adopts the cen…