paper-with-me

Papers

CPPO: Continual Learning for Reinforcement Learning with Human Feedback

2024-01-16 · Conference 2024 1 · Han Zhang, Yu Lei, Lin Gui, Min Yang, Yulan He, Hui Wang, Ruifeng Xu

The approach of Reinforcement Learning from Human Feedback (RLHF) is widely used for enhancing pre-trained Language Models (LM), enabling them to better align with human preferences. Existing RLHF-based LMs however require complete retraining whenever new queries or feedback are introduced, as human preferences may differ across different domains or topics. LM retraining is often impracticable in most real-world scenarios, due to the substantial time and computational costs involved, as well as data privacy concerns. To address this limitation, we propose Continual Proximal Policy Optimization (CPPO), a novel method that is able to continually align LM with dynamic human preferences. Specifically, CPPO adopts a weighting strategy to decide which samples should be utilized for enhancing policy learning and which should be used for solidifying past experiences. This seeks a good trade-off between policy learning and knowledge retention. Our experimental results show that CPPO outperforms strong Continuous learning (CL) baselines when it comes to consistently aligning with human preferences. Furthermore, compared to PPO, CPPO offers more efficient and stable learning in non-continual scenarios.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learningreinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism

2023-05-29 · Zihao Li, Zhuoran Yang, Mengdi Wang

In this paper, we study offline Reinforcement Learning with Human Feedback (RLHF) where we aim to learn the human's underlying reward and the MDP's optimal policy from a set of trajectories induced by human choices. RLHF…

Decision MakingEconometricsOffline RLreinforcement-learning+1

Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation

2026-05-13 · Asim Osman, Sasha Abramowitz, Mark Bergh, Ulrich Armel Mbou Sob 외 arxiv

Contrastive reinforcement learning (CRL) learns goal-conditioned Q-values through a contrastive objective over state-action and goal representations, removing the need for hand-crafted reward functions. Despite impressiv…

Self-Supervised LearningReinforcement Learning

CPPO: Contrastive Perception Policy Optimization for VLM Agents

2026-01-01 · Ahmad Rezaei, Mohsen Gholami, Saeed Ranjbar Alvar, Kevin Cannons 외 arxiv

We introduce CPPO, a Contrastive Perception Policy Optimization method for finetuning vision--language models (VLMs). Reliable perception is a core requirement for VLM-based agents that must reason and act in open-ended …

Reinforcement LearningVisual Grounding

Pref-GUIDE: Continual Policy Learning from Real-Time Human Feedback via Preference-Based Learning

2025-08-10 · Zhengran Ji, Boyuan Chen arxiv

Training reinforcement learning agents with human feedback is crucial when task objectives are difficult to specify through dense reward functions. While prior methods rely on offline trajectory comparisons to elicit hum…

Reinforcement Learning

Towards Safe Reinforcement Learning via Constraining Conditional Value at Risk

2021-06-18 · ICML Workshop AML 2021 7 · Chengyang Ying, Xinning Zhou, Dong Yan, Jun Zhu

Though deep reinforcement learning (DRL) has obtained substantial success, it may encounter catastrophic failures due to the intrinsic uncertainty caused by stochastic policies and environment variability. To address thi…

continuous-controlContinuous ControlDeep Reinforcement LearningMuJoCo+4