paper-with-me

Papers

The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure

2022-05-20 · Xing Chen, Dongcui Diao, Hechang Chen, Hengshuai Yao, Haiyin Piao, Zhixiao Sun, Zhiwei Yang, Randy Goebel, Bei Jiang, Yi Chang

The popular Proximal Policy Optimization (PPO) algorithm approximates the solution in a clipped policy space. Does there exist better policies outside of this space? By using a novel surrogate objective that employs the sigmoid function (which provides an interesting way of exploration), we found that the answer is `YES'', and the better policies are in fact located very far from the clipped space. We show that PPO is insufficient in `off-policyness'', according to an off-policy metric called DEON. Our algorithm explores in a much larger policy space than PPO, and it maximizes the Conservative Policy Iteration (CPI) objective better than PPO during training. To the best of our knowledge, all current PPO methods have the clipping operation and optimize in the clipped policy space. Our method is the first of this kind, which advances the understanding of CPI optimization and policy gradient methods. Code is available at https://github.com/raincchio/P3O.

📄 PDF Abstract BibTeX arXiv:2205.10047

Code (1)

raincchio/p3o 공식 구현 tf

Tasks

Efficient ExplorationPolicy Gradient Methods

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…

Similar Papers 제목 키워드 기반

SoftAdaClip: A Smooth Clipping Strategy for Fair and Private Model Training

2025-10-01 · Dorsa Soleymani, Ali Dadsetan, Frank Rudzicz arxiv

Differential privacy (DP) provides strong protection for sensitive data, but often reduces model performance and fairness, especially for underrepresented groups. One major reason is gradient clipping in DP-SGD, which ca…

SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training

2026-03-09 · Xin-Cheng Wen, Binbin Chen, Haoxuan Lan, Hang Yu 외 arxiv

Large language models (LLMs) have transformed the software engineering landscape. Recently, numerous LLM-based agents have been developed to address real-world software issue fixing tasks. Despite their state-of-the-art …

It's Not You, It's Clipping: A Soft Trust-Region via Probability Smoothing for LLM RL

2025-09-25 · Madeleine Dwyer, Adam Sobey, Adriane Chapman arxiv

Training large language models (LLMs) with reinforcement learning (RL) methods such as PPO and GRPO commonly relies on ratio clipping to stabilise updates. While effective at preventing instability, clipping discards inf…

Reinforcement LearningMathematical Reasoning

From $\log π$ to $π$: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight

2026-03-15 · Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Chaowen Hu 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed a leap in Large Language Model (LLM) reasoning, yet its optimization dynamics remain fragile. Standard algorithms like GRPO enforce stability via "hard …

Reinforcement Learning

Incorporating Attribution Importance for Improving Faithfulness Metrics

2023-05-17 · Zhixue Zhao, Nikolaos Aletras

Feature attribution methods (FAs) are popular approaches for providing insights into the model reasoning process of making predictions. The more faithful a FA is, the more accurately it reflects which parts of the input …