English
Related papers

Related papers: Compatible Natural Gradient Policy Search

200 papers

It remains challenging to deploy existing risk-averse approaches to real-world applications. The reasons are multi-fold, including the lack of global optimality guarantee and the necessity of learning from long-term consecutive…

Machine Learning · Computer Science 2022-07-25 Liangliang Xu , Daoming Lyu , Yangchen Pan , Aiwen Jiang , Bo Liu

Reinforcement learning (RL) has become a powerful paradigm for optimizing large language models (LLMs) to handle complex reasoning tasks. A core challenge in this process lies in managing policy entropy, which reflects the balance between…

Machine Learning · Computer Science 2026-04-24 Zhenpeng Su , Leiyu Pan , Minxuan Lv , Yuntao Li , Wenping Hu , Fuzheng Zhang , Kun Gai , Guorui Zhou

Direct policy gradient methods for reinforcement learning are a successful approach for a variety of reasons: they are model free, they directly optimize the performance metric of interest, and they allow for richly parameterized policies.…

Machine Learning · Computer Science 2020-08-14 Alekh Agarwal , Mikael Henaff , Sham Kakade , Wen Sun

While policy optimization algorithms have played an important role in recent empirical success of Reinforcement Learning (RL), the existing theoretical understanding of policy optimization remains rather limited -- they are either…

Machine Learning · Computer Science 2023-12-05 Qinghua Liu , Gellért Weisz , András György , Chi Jin , Csaba Szepesvári

We consider descent methods for solving non-finite valued nonsmooth convex-composite optimization problems that employ Gauss-Newton subproblems to determine the iteration update. Specifically, we establish the global convergence properties…

Optimization and Control · Mathematics 2019-09-11 James V. Burke , Abraham Engle

On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on a single solution once discovered and ceasing exploration of alternative strategies. We…

Artificial Intelligence · Computer Science 2026-05-20 Xiaozhe Li , Yang Li , Xinyu Fang , Shengyuan Ding , Peiji Li , Yongkang Chen , Yichuan Ma , Tianyi Lyu , Linyang Li , Dahua Lin , Qipeng Guo , Qingwen Liu , Kai Chen

We study the convergence of several natural policy gradient (NPG) methods in infinite-horizon discounted Markov decision processes with regular policy parametrizations. For a variety of NPGs and reward functions we show that the…

Optimization and Control · Mathematics 2024-02-21 Johannes Müller , Guido Montúfar

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

Online tree-based search algorithms iteratively simulate trajectories and update action-values for a set of states stored in a tree structure. It works reasonably well in practice but fails to effectively utilise the information gathered…

Artificial Intelligence · Computer Science 2023-03-07 Dixant Mittal , Siddharth Aravindan , Wee Sun Lee

We revisit the Reinforce policy gradient algorithm from the literature. Note that this algorithm typically works with cost returns obtained over random length episodes obtained from either termination upon reaching a goal state (as with…

Machine Learning · Computer Science 2023-10-10 Shalabh Bhatnagar

Searching large and complex design spaces for a global optimum can be infeasible and unnecessary. A practical alternative is to iteratively refine the neighborhood of an initial design using local optimization methods such as gradient…

Machine Learning · Computer Science 2025-11-25 David Stenger , Armin Lindicke , Alexander von Rohr , Sebastian Trimpe

In the pursuit of finding an optimal policy, reinforcement learning (RL) methods generally ignore the properties of learned policies apart from their expected return. Thus, even when successful, it is difficult to characterize which…

Machine Learning · Computer Science 2025-10-10 Yash Jhaveri , Harley Wiltzer , Patrick Shafto , Marc G. Bellemare , David Meger

We study online policy optimization in nonlinear time-varying dynamical systems where the true dynamical models are unknown to the controller. This problem is challenging because, unlike in linear systems, the controller cannot obtain…

Optimization and Control · Mathematics 2024-04-22 Yiheng Lin , James A. Preiss , Fengze Xie , Emile Anand , Soon-Jo Chung , Yisong Yue , Adam Wierman

Scaling reinforcement learning to tens of thousands of parallel environments requires overcoming the limited exploration capacity of a single policy. Ensemble-based policy gradient methods, which employ multiple policies to collect diverse…

Machine Learning · Computer Science 2026-03-04 Naoki Shitanda , Motoki Omura , Tatsuya Harada , Takayuki Osa

Natural policy gradient (NPG) methods with entropy regularization achieve impressive empirical success in reinforcement learning problems with large state-action spaces. However, their convergence properties and the impact of entropy…

Machine Learning · Computer Science 2026-02-17 Semih Cayci , Niao He , R. Srikant

Cooperative games are those in which both agents share the same payoff structure. Value-based reinforcement-learning algorithms, such as variants of Q-learning, have been applied to learning cooperative games, but they only apply when the…

Machine Learning · Computer Science 2017-05-25 Leonid Peshkin , Kee-Eung Kim , Nicolas Meuleau , Leslie Pack Kaelbling

Cooperative games are those in which both agents share the same payoff structure. Value-based reinforcement-learning algorithms, such as variants of Q-learning, have been applied to learning cooperative games, but they only apply when the…

Artificial Intelligence · Computer Science 2014-08-08 Leonid Peshkin , Kee-Eung Kim , Nicolas Meuleau , Leslie Pack Kaelbling

Standard reinforcement learning methods aim to master one way of solving a task whereas there may exist multiple near-optimal policies. Being able to identify this collection of near-optimal policies can allow a domain expert to efficiently…

Machine Learning · Computer Science 2019-06-04 Muhammad A. Masood , Finale Doshi-Velez

Group Relative Policy Optimization (GRPO) was introduced and used recently for promoting reasoning in LLMs under verifiable (binary) rewards. We show that the mean + variance calibration of these rewards induces a weighted contrastive loss…

Machine Learning · Computer Science 2025-10-22 Youssef Mroueh

In this paper, we revisit and improve the convergence of policy gradient (PG), natural PG (NPG) methods, and their variance-reduced variants, under general smooth policy parametrizations. More specifically, with the Fisher information…

Machine Learning · Computer Science 2022-11-17 Yanli Liu , Kaiqing Zhang , Tamer Başar , Wotao Yin