OSS Mentor A framework for improving developers contributions via deep reinforcement learning

2022-10-24 · Jiakuan Fan, Haoyue Wang, Wei Wang, Ming Gao, Shengyu Zhao

In open source project governance, there has been a lot of concern about how to measure developers' contributions. However, extremely sparse work has focused on enabling developers to improve their contributions, while it is significant and valuable. In this paper, we introduce a deep reinforcement learning framework named Open Source Software(OSS) Mentor, which can be trained from empirical knowledge and then adaptively help developers improve their contributions. Extensive experiments demonstrate that OSS Mentor significantly outperforms excellent experimental results. Moreover, it is the first time that the presented framework explores deep reinforcement learning techniques to manage open source software, which enables us to design a more robust framework to improve developers' contributions.

📄 PDF Abstract BibTeX arXiv:2210.13990

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

MENTOR: Guiding Hierarchical Reinforcement Learning with Human Feedback and Dynamic Distance Constraint

2024-02-22 · Xinglin Zhou, Yifu Yuan, Shaofu Yang, Jianye Hao

Hierarchical reinforcement learning (HRL) provides a promising solution for complex tasks with sparse rewards of intelligent agents, which uses a hierarchical framework that divides tasks into subgoals and completes them…

Hierarchical Reinforcement Learning reinforcement-learning Reinforcement Learning

MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning

2024-10-19 · Suning Huang, Zheyu Zhang, Tianhai Liang, Yihan Xu 외

Visual deep reinforcement learning (RL) enables robots to acquire skills from visual input for unstructured tasks. However, current algorithms suffer from low sample efficiency, limiting their practical applicability. In…

Deep Reinforcement Learning Mixture-of-Experts Reinforcement Learning (RL)

MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation

2025-10-21 · ChangSu Choi, Hoyun Song, Dongyeon Kim, WooHyeon Jung 외 arxiv

Distilling the tool-use capabilities of large language models (LLMs) into small language models (SLMs) is essential for their practical application. The predominant approach, supervised fine-tuning (SFT), is an off-polic…

Reinforcement Learning

Golden Handcuffs make safer AI agents

2026-04-15 · Aram Ebtekar, Michael K. Cohen arxiv

Reinforcement learners can attain high reward through novel unintended strategies. We study a Bayesian mitigation for general environments: we expand the agent's subjective reward range to include a large negative value …

HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving

2024-01-06 · Zilin Huang, Zihao Sheng, Chengyuan Ma, Sikai Chen

Despite significant progress in autonomous vehicles (AVs), the development of driving policies that ensure both the safety of AVs and traffic flow efficiency has not yet been fully explored. In this paper, we propose an …

AI Agent Autonomous Driving Autonomous Vehicles Deep Reinforcement Learning+1