English
Related papers

Related papers: Revisiting Design Choices in Proximal Policy Optim…

200 papers

Direct Preference Optimization (DPO) has become a widely used training method for the instruction fine-tuning of large language models (LLMs). In this work, we explore an under-investigated aspect of DPO - its dependency on the reference…

Computation and Language · Computer Science 2024-08-23 Yixin Liu , Pengfei Liu , Arman Cohan

We propose Process-Aware Policy Optimization (PAPO), a method that integrates process-level evaluation into Group Relative Policy Optimization (GRPO) through decoupled advantage normalization, to address two limitations of existing reward…

Artificial Intelligence · Computer Science 2026-04-06 Zelin Tan , Zhouliang Yu , Bohan Lin , Zijie Geng , Hejia Geng , Yudong Zhang , Mulei Zhang , Yang Chen , Shuyue Hu , Zhenfei Yin , Chen Zhang , Lei Bai

Most reinforcement learning methods rely heavily on dense, well-normalized environment rewards. DreamerV3 recently introduced a model-based method with a number of tricks that mitigate these limitations, achieving state-of-the-art on a wide…

Machine Learning · Computer Science 2023-10-30 Ryan Sullivan , Akarsh Kumar , Shengyi Huang , John P. Dickerson , Joseph Suarez

Large Language Models (LLMs) have demonstrated remarkable potential in automating software development tasks. While recent advances leverage Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) to align models with human…

Software Engineering · Computer Science 2025-12-09 Xin Yin , Chao Ni , Xiaohu Yang

Direct Preference Optimization (DPO) and its variants have become the de facto standards for aligning large language models (LLMs) with human preferences or specific goals. However, DPO requires high-quality preference data and suffers from…

Machine Learning · Computer Science 2024-11-12 Zhuotong Chen , Fang Liu , Jennifer Zhu , Wanyu Du , Yanjun Qi

In recent years, reinforcement learning (RL) has gained increasing attention in control engineering. Especially, policy gradient methods are widely used. In this work, we improve the tracking performance of proximal policy optimization…

Machine Learning · Computer Science 2021-07-21 Jana Mayer , Johannes Westermann , Juan Pedro Gutiérrez H. Muriedas , Uwe Mettin , Alexander Lampe

Proximal policy optimization (PPO) approximates the trust region update using multiple epochs of clipped SGD. Each epoch may drift further from the natural gradient direction, creating path-dependent noise. To understand this drift, we can…

Machine Learning · Computer Science 2026-03-16 Zelal Su , Mustafaoglu , Sungyoung Lee , Eshan Balachandar , Risto Miikkulainen , Keshav Pingali

Proximal Policy Optimization (PPO) has become the de facto standard for training legged robots, thanks to its robustness and scalability in massively parallel simulation environments like IsaacLab. However, its on-policy nature makes it…

Robotics · Computer Science 2026-05-26 Gianluca Sabatini , Chenhao Li , Marco Hutter

Most of reinforcement learning algorithms optimize the discounted criterion which is beneficial to accelerate the convergence and reduce the variance of estimates. Although the discounted criterion is appropriate for certain tasks such as…

Machine Learning · Computer Science 2021-11-02 Xiaoteng Ma , Xiaohang Tang , Li Xia , Jun Yang , Qianchuan Zhao

Reinforcement learning (RL) is inherently rife with non-stationarity since the states and rewards the agent observes during training depend on its changing policy. Therefore, networks in deep RL must be capable of adapting to new…

Machine Learning · Computer Science 2024-11-21 Skander Moalla , Andrea Miele , Daniil Pyatko , Razvan Pascanu , Caglar Gulcehre

In neural combinatorial optimization (CO), reinforcement learning (RL) can turn a deep neural net into a fast, powerful heuristic solver of NP-hard problems. This approach has a great potential in practical applications because it allows…

Machine Learning · Computer Science 2021-07-14 Yeong-Dae Kwon , Jinho Choo , Byoungjip Kim , Iljoo Yoon , Youngjune Gwon , Seungjai Min

Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard token-level PPO struggles in this setting due to the instability of temporal credit…

Artificial Intelligence · Computer Science 2026-04-13 Tianyi Wang , Yixia Li , Long Li , Yibiao Chen , Shaohan Huang , Yun Chen , Peng Li , Yang Liu , Guanhua Chen

Direct Preference Optimization (DPO) has been proposed as a promising alternative to Proximal Policy Optimization (PPO) based Reinforcement Learning with Human Feedback (RLHF). However, empirical evaluations consistently reveal suboptimal…

Machine Learning · Computer Science 2025-03-03 Qinwei Ma , Jingzhe Shi , Can Jin , Jenq-Neng Hwang , Serge Belongie , Lei Li

Reinforcement learning (RL) is pivotal for enabling large language models (LLMs) to generate long chains of thought (CoT) for complex tasks like math and reasoning. However, Proximal Policy Optimization (PPO), effective in many RL…

Machine Learning · Computer Science 2025-03-04 Yufeng Yuan , Yu Yue , Ruofei Zhu , Tiantian Fan , Lin Yan

In this paper, we propose a new algorithm PPG (Proximal Policy Gradient), which is close to both VPG (vanilla policy gradient) and PPO (proximal policy optimization). The PPG objective is a partial variation of the VPG objective and the…

Machine Learning · Computer Science 2020-10-21 Ju-Seung Byun , Byungmoon Kim , Huamin Wang

Evaluating preference optimization (PO) algorithms on LLM alignment is a challenging task that presents prohibitive costs, noise, and several variables like model size and hyper-parameters. In this work, we show that it is possible to gain…

Machine Learning · Computer Science 2026-01-09 Carlo Alfano , Silvia Sapora , Jakob Nicolaus Foerster , Patrick Rebeschini , Yee Whye Teh

In this paper, we study the global optimality of polynomial portfolio optimization (PPO). The PPO is a kind of portfolio selection model with high-order moments and flexible risk preference parameters. We introduce a perturbation sample…

Optimization and Control · Mathematics 2023-09-06 Liu Yang , Yi Yang , Suhan Zhong

We evaluate benchmark deep reinforcement learning algorithms on the task of portfolio optimisation using simulated data. The simulator to generate the data is based on correlated geometric Brownian motion with the Bertsimas-Lo market impact…

Computational Engineering, Finance, and Science · Computer Science 2025-08-07 Chung I Lu

Proximal Policy Optimization (PPO), a popular on-policy deep reinforcement learning method, employs a stochastic policy for exploration. In this paper, we propose a colored noise-based stochastic policy variant of PPO. Previous research…

Machine Learning · Computer Science 2024-06-18 Jakob Hollenstein , Georg Martius , Justus Piater

Deep reinforcement learning is prone to overfitting, and traditional benchmarks such as Atari 2600 benchmark can exacerbate this problem. The Obstacle Tower Challenge addresses this by using randomized environments and separate seeds for…

Machine Learning · Computer Science 2019-07-29 Joe Booth