paper-with-me

Papers

Efficient Preference-based Reinforcement Learning via Aligned Experience Estimation

2024-05-29 · Fengshuo Bai, Rui Zhao, Hongming Zhang, Sijia Cui, Ying Wen, Yaodong Yang, Bo Xu, Lei Han

Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. However, a notable limitation of PbRL is its dependency on substantial human feedback. This dependency stems from the learning loop, which entails accurate reward learning compounded with value/policy learning, necessitating a considerable number of samples. To boost the learning loop, we propose SEER, an efficient PbRL method that integrates label smoothing and policy regularization techniques. Label smoothing reduces overfitting of the reward model by smoothing human preference labels. Additionally, we bootstrap a conservative estimate $\widehat{Q}$ using well-supported state-action pairs from the current replay memory to mitigate overestimation bias and utilize it for policy learning regularization. Our experimental results across a variety of complex tasks, both in online and offline settings, demonstrate that our approach improves feedback efficiency, outperforming state-of-the-art methods by a large margin. Ablation studies further reveal that SEER achieves a more accurate Q-function compared to prior work.

📄 PDF Abstract BibTeX arXiv:2405.18688

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Sigmoid Activation 설명 없음
LARS Layer-wise Adaptive Rate Scaling, or LARS, is a large batch optimization technique. There are two notable differences between LARS and other adaptive algorithms such as…
Squeeze-and-Excitation Block The Squeeze-and-Excitation Block is an architectural unit designed to improve the representational power of a network by enabling it to perform dynamic channel-wise feature…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Average Pooling 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Similar Papers 제목 키워드 기반

f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment

2026-02-05 · Rajdeep Haldar, Lantao Mei, Guang Lin, Yue Xing 외 arxiv

Recent work shows that preference alignment objectives can be interpreted as divergence estimators between aligned (preferred) & unaligned (less-preferred) distributions, yielding a principled recipe for designing alignm…

Reinforcement Learning

Toward Preference-aligned Large Language Models via Residual-based Model Steering

2025-09-28 · Lucio La Cava, Andrea Tagarelli arxiv

Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences. Existing approaches such as Reinforcement Learning from Human Feedback or Direct Preference Opti…

Reinforcement LearningMathematical ReasoningCode Generation

CoRe: Combined Rewards with Vision-Language Model Feedback for Preference-Aligned Reinforcement Learning

2026-07-02 · Hexian Ni, Tao Lu, Yinghao Cai arxiv

Reward design remains a central challenge in reinforcement learning (RL). Hand-crafted rewards are often difficult to specify and may lead to suboptimal policies, while learned rewards from preferences can suffer from in…

Reinforcement Learning

Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning

2026-04-15 · Qin Zhou, Guoyan Liang, Qianyi Yang, Jingyuan Chen 외 arxiv

Recent reinforcement learning (RL) approaches have advanced radiology report generation (RRG), yet two core limitations persist: (1) report-level rewards offer limited evidence-grounded guidance for clinical faithfulness…

Reinforcement Learning

TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance

2025-10-09 · Jianhui Yang, Yiming Jin, Pengkun Jiao, Chenhe Dong 외 arxiv

Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping, where semantic understanding and complex reasoning directly shape the user exper…

Reinforcement Learning