paper-with-me

홈 › Papers

Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generation

2024-03-20 · Do June Min, Veronica Perez-Rosas, Kenneth Resnicow, Rada Mihalcea

In this paper, we study the problem of multi-reward reinforcement learning to jointly optimize for multiple text qualities for natural language generation. We focus on the task of counselor reflection generation, where we optimize the generators to simultaneously improve the fluency, coherence, and reflection quality of generated counselor responses. We introduce two novel bandit methods, DynaOpt and C-DynaOpt, which rely on the broad strategy of combining rewards into a single value and optimizing them simultaneously. Specifically, we employ non-contextual and contextual multi-arm bandits to dynamically adjust multiple reward weights during training. Through automatic and manual evaluations, we show that our proposed techniques, DynaOpt and C-DynaOpt, outperform existing naive and bandit baselines, showcasing their potential for enhancing language models.

📄 PDF Abstract BibTeX arXiv:2403.13578

Code (1)

michigannlp/dynaopt 공식 구현 pytorch

Tasks

Text Generation

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment

2024-02-15 · Rui Yang, Xiaoman Pan, Feng Luo, Shuang Qiu 외

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 generally costly and unstable to fine-tun…

GPUReinforcement Learning (RL)

Dual Action Policy for Robust Sim-to-Real Reinforcement Learning

2024-10-16 · Ng Wen Zheng Terence, Chen Jianda

This paper presents Dual Action Policy (DAP), a novel approach to address the dynamics mismatch inherent in the sim-to-real gap of reinforcement learning. DAP uses a single policy to predict two sets of actions: one for …

Domain Adaptation

Reward-Conditioned Reinforcement Learning

2026-03-05 · Michal Nauman, Marek Cygan, Pieter Abbeel arxiv

Single-task RL agents are typically trained under a fixed reward function, which limits their robustness to reward misspecification and their ability to adapt to changing preferences. We introduce Reward-Conditioned Rein…

Reinforcement LearningMulti-Task Learning

Reward-Relevance-Filtered Linear Offline Reinforcement Learning

2024-01-23 · Angela Zhou

This paper studies offline reinforcement learning with linear function approximation in a setting with decision-theoretic, but not estimation sparsity. The structural restrictions of the data-generating process presume t…

reinforcement-learningReinforcement Learning

Hindsight Reward Tweaking via Conditional Deep Reinforcement Learning

2021-09-06 · Ning Wei, Jiahua Liang, Di Xie, ShiLiang Pu

Designing optimal reward functions has been desired but extremely difficult in reinforcement learning (RL). When it comes to modern complex tasks, sophisticated reward functions are widely used to simplify policy learnin…

Deep Reinforcement LearningMuJoCoreinforcement-learningReinforcement Learning+1