English
Related papers

Related papers: Approximation of Log-Partition Function in Policy …

200 papers

Policy optimization methods like Group Relative Policy Optimization (GRPO) and its variants have achieved strong results on mathematical reasoning and code generation tasks. Despite extensive exploration of reward processing strategies and…

Machine Learning · Computer Science 2026-02-05 Rui Yuan , Mykola Khandoga , Vinay Kumar Sankarapu

Reinforcement learning (RL) post-training is crucial for LLM alignment and reasoning, but existing policy-based methods, such as PPO and DPO, can fall short of fixing shortcuts inherited from pre-training. In this work, we introduce…

Machine Learning · Computer Science 2025-10-21 Jin Peng Zhou , Kaiwen Wang , Jonathan Chang , Zhaolin Gao , Nathan Kallus , Kilian Q. Weinberger , Kianté Brantley , Wen Sun

Tremendous progress has been made in reinforcement learning (RL) over the past decade. Most of these advancements came through the continual development of new algorithms, which were designed using a combination of mathematical derivations,…

Machine Learning · Computer Science 2022-10-14 Chris Lu , Jakub Grudzien Kuba , Alistair Letcher , Luke Metz , Christian Schroeder de Witt , Jakob Foerster

Proximal Policy Optimization (PPO) is commonly used in Reinforcement Learning from Human Feedback to align large language models (LLMs) with downstream tasks. This paper investigates the feasibility of using PPO for direct reinforcement…

Computation and Language · Computer Science 2024-10-23 Alexander G. Padula , Dennis J. N. J. Soemers

Despite perfectly interpolating the training data, deep neural networks (DNNs) can often generalize fairly well, in part due to the "implicit regularization" induced by the learning algorithm. Nonetheless, various forms of regularization,…

Machine Learning · Computer Science 2022-02-23 Navid Azizan , Sahin Lale , Babak Hassibi

Offline Reinforcement Learning (RL) aims to learn a near-optimal policy from a fixed dataset of transitions collected by another policy. This problem has attracted a lot of attention recently, but most existing methods with strong…

Machine Learning · Computer Science 2023-05-23 Germano Gabbianelli , Gergely Neu , Nneka Okolo , Matteo Papini

Reinforcement learning (RL) struggles to scale to large, combinatorial action spaces common in many real-world problems. This paper introduces a novel framework for training discrete diffusion models as highly effective policies in these…

Machine Learning · Computer Science 2026-05-21 Haitong Ma , Ofir Nabati , Aviv Rosenberg , Bo Dai , Oran Lang , Craig Boutilier , Na Li , Shie Mannor , Lior Shani , Guy Tenneholtz

Policy gradient algorithms have been successfully applied to enhance the reasoning capabilities of large language models (LLMs). KL regularization is ubiquitous, yet the design surface, choice of KL direction (forward vs. reverse),…

Machine Learning · Computer Science 2026-02-20 Yifan Zhang , Yifeng Liu , Huizhuo Yuan , Yang Yuan , Quanquan Gu , Andrew Chi-Chih Yao

We develop a generic policy gradient method with the global optimality guarantee for robust Markov Decision Processes (MDPs). While policy gradient methods are widely used for solving dynamic decision problems due to their scalable and…

Machine Learning · Computer Science 2024-11-01 Qiuhao Wang , Shaohang Xu , Chin Pang Ho , Marek Petrik

In this short note, we give the convergence analysis of the policy in the recent famous policy mirror descent (PMD). We mainly consider the unregularized setting following [11] with generalized Bregman divergence. The difference is that we…

Optimization and Control · Mathematics 2024-06-04 Dachao Lin , Zhihua Zhang

Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio…

Machine Learning · Computer Science 2026-05-27 Penghui Qi , Xiangxin Zhou , Zichen Liu , Tianyu Pang , Chao Du , Min Lin , Wee Sun Lee

Safety is an essential requirement for reinforcement learning systems. The newly emerging framework of robust constrained Markov decision processes allows learning policies that satisfy long-term constraints while providing guarantees under…

Machine Learning · Computer Science 2025-12-19 David M. Bossens , Atsushi Nitanda

It is commonly believed that optimizing the reverse KL divergence results in "mode seeking", while optimizing forward KL results in "mass covering", with the latter being preferred if the goal is to sample from multiple diverse modes. We…

Machine Learning · Computer Science 2025-10-24 Anthony GX-Chen , Jatin Prakash , Jeff Guo , Rob Fergus , Rajesh Ranganath

Large language models (LLMs) have shown promise in performing complex multi-step reasoning, yet they continue to struggle with mathematical reasoning, often making systematic errors. A promising solution is reinforcement learning (RL)…

Machine Learning · Computer Science 2025-09-22 Hanning Zhang , Pengcheng Wang , Shizhe Diao , Yong Lin , Rui Pan , Hanze Dong , Dylan Zhang , Pavlo Molchanov , Tong Zhang

Policy evaluation or value function or Q-function approximation is a key procedure in reinforcement learning (RL). It is a necessary component of policy iteration and can be used for variance reduction in policy gradient methods. Therefore…

Machine Learning · Computer Science 2017-10-17 Xinyan Yan , Krzysztof Choromanski , Byron Boots , Vikas Sindhwani

Recently, adversarial imitation learning has shown a scalable reward acquisition method for inverse reinforcement learning (IRL) problems. However, estimated reward signals often become uncertain and fail to train a reliable statistical…

Machine Learning · Computer Science 2023-01-06 Dong-Sig Han , Hyunseo Kim , Hyundo Lee , Je-Hwan Ryu , Byoung-Tak Zhang

Recent advances in rule-based reinforcement learning (RL) have significantly improved the reasoning capability of language models (LMs) with rule-based rewards. However, existing RL methods -- such as GRPO, REINFORCE++, and RLOO -- often…

Machine Learning · Computer Science 2025-05-20 Zongkai Liu , Fanqing Meng , Lingxiao Du , Zhixiang Zhou , Chao Yu , Wenqi Shao , Qiaosheng Zhang

Reinforcement learning algorithms for mean-field games offer a scalable framework for optimizing policies in large populations of interacting agents. Existing methods often depend on online interactions or access to system dynamics,…

Machine Learning · Computer Science 2024-10-24 Axel Brunnbauer , Julian Lemmel , Zahra Babaiee , Sophie Neubauer , Radu Grosu

Modern deep reinforcement learning (RL) algorithms are motivated by either the generalised policy iteration (GPI) or trust-region learning (TRL) frameworks. However, algorithms that strictly respect these theoretical frameworks have proven…

Machine Learning · Computer Science 2024-11-21 Jakub Grudzien Kuba , Christian Schroeder de Witt , Jakob Foerster

We study the problem of Inverse Reinforcement Learning (IRL) with an average-reward criterion. The goal is to recover an unknown policy and a reward function when the agent only has samples of states and actions from an experienced agent.…

Machine Learning · Computer Science 2023-05-25 Feiyang Wu , Jingyang Ke , Anqi Wu