English
Related papers

Related papers: Post-Training with Policy Gradients: Optimality an…

200 papers

In reinforcement learning from human feedback, preference-based reward models play a central role in aligning large language models to human-aligned behavior. However, recent studies show that these models are prone to reward hacking and…

Artificial Intelligence · Computer Science 2025-10-23 Wenqian Ye , Guangtao Zheng , Aidong Zhang

Reinforcement Learning (RL) has shown great potential in refining robotic manipulation policies, yet its efficacy remains strongly bottlenecked by the difficulty of designing generalizable reward functions. In this paper, we propose a…

Robotics · Computer Science 2026-03-24 Yanru Wu , Weiduo Yuan , Ang Qi , Vitor Guizilini , Jiageng Mao , Yue Wang

Learning reward models from pairwise comparisons is a fundamental component in a number of domains, including autonomous control, conversational agents, and recommendation systems, as part of a broad goal of aligning automated decisions…

Machine Learning · Computer Science 2024-10-10 Junlin Wu , Jiongxiao Wang , Chaowei Xiao , Chenguang Wang , Ning Zhang , Yevgeniy Vorobeychik

Safety post-training can improve the harmfulness and policy compliance of Large Language Models (LLMs), but it may also reduce general utility, a phenomenon often described as the \emph{alignment tax}. We study this trade-off through the…

Machine Learning · Computer Science 2026-05-13 Guanglong Sun , Siyuan Zhang , Liyuan Wang , Jun Zhu , Hang Su , Yi Zhong

Policy-based methods have achieved remarkable success in solving challenging reinforcement learning problems. Among these methods, off-policy policy gradient methods are particularly important due to that they can benefit from off-policy…

Machine Learning · Computer Science 2024-05-07 Wenjia Meng , Qian Zheng , Long Yang , Yilong Yin , Gang Pan

Reinforcement learning with verifiable reward has recently emerged as a central paradigm for post-training large language models (LLMs); however, prevailing mean-based methods, such as Group Relative Policy Optimization (GRPO), suffer from…

Machine Learning · Computer Science 2025-10-02 Tao Ren , Jinyang Jiang , Hui Yang , Wan Tian , Minhao Zou , Guanghao Li , Zishi Zhang , Qinghao Wang , Shentao Qin , Yanjun Zhao , Rui Tao , Hui Shao , Yijie Peng

Reinforcement learning (RL) with outcome-based rewards has proven effective for improving large language models (LLMs) on complex reasoning tasks. However, its success often depends on the base model occasionally sampling correct solutions.…

Machine Learning · Computer Science 2025-10-07 Jatin Prakash , Anirudh Buvanesh

Policy gradient (PG) methods have played an essential role in the empirical successes of reinforcement learning. In order to handle large state-action spaces, PG methods are typically used with function approximation. In this setting, the…

State-of-the-art model-based reinforcement learning methods train policies on imagined rollouts. These rollouts are trajectories generated by a learned dynamics model and are scored by a learned reward model, but without querying the true…

Machine Learning · Computer Science 2026-05-13 Nadav Timor , Ravid Shwartz-Ziv , Micah Goldblum , Yann LeCun , David Harel

Goal-conditioned policies enable decision-making models to execute diverse behaviors based on specified goals, yet their downstream performance is often highly sensitive to the choice of instructions or prompts. To bypass the limitations of…

Artificial Intelligence · Computer Science 2026-05-04 Guangyu Zhao , Kewei Lian , Haoxuan Ru , Borong Zhang , Haowei Lin , Zhancun Mu , Haobo Fu , Qiang Fu , Shaofei Cai , Zihao Wang , Yitao Liang

Reinforcement Learning and Imitation Learning have achieved widespread success in many domains but remain constrained during real-world deployment. One of the main issues is the additional requirements that were not considered during…

Machine Learning · Computer Science 2025-05-26 Pengcheng Wang , Xinghao Zhu , Yuxin Chen , Chenfeng Xu , Masayoshi Tomizuka , Chenran Li

We consider the problem of contextual bandits and imitation learning, where the learner lacks direct knowledge of the executed action's reward. Instead, the learner can actively query an expert at each round to compare two actions and…

Machine Learning · Computer Science 2023-07-25 Ayush Sekhari , Karthik Sridharan , Wen Sun , Runzhe Wu

Existing alignment methods directly use the reward model learned from user preference data to optimize an LLM policy, subject to KL regularization with respect to the base policy. This practice is suboptimal for maximizing user's utility…

Machine Learning · Computer Science 2026-02-04 Haichuan Wang , Tao Lin , Lingkai Kong , Ce Li , Hezi Jiang , Milind Tambe

This paper augments the reward received by a reinforcement learning agent with potential functions in order to help the agent learn (possibly stochastic) optimal policies. We show that a potential-based reward shaping scheme is able to…

Machine Learning · Computer Science 2019-07-23 Baicen Xiao , Bhaskar Ramasubramanian , Andrew Clark , Hannaneh Hajishirzi , Linda Bushnell , Radha Poovendran

We study the problem of learning to generate an answer (or completion) to a question (or prompt), where there could be multiple correct answers, any one of which is acceptable at test time. Learning is based on demonstrations of some…

Machine Learning · Computer Science 2026-02-27 Nirmit Joshi , Gene Li , Siddharth Bhandari , Shiva Prasad Kasiviswanathan , Cong Ma , Nathan Srebro

Reinforcement learning algorithms are fundamental to align large language models with human preferences and to enhance their reasoning capabilities. However, current reinforcement learning algorithms often suffer from training instability…

Machine Learning · Computer Science 2025-06-05 Yaru Hao , Li Dong , Xun Wu , Shaohan Huang , Zewen Chi , Furu Wei

The inherent uncertainty in the environmental transition model of Reinforcement Learning (RL) necessitates a delicate balance between exploration and exploitation. This balance is crucial for optimizing computational resources to accurately…

Machine Learning · Computer Science 2025-05-21 Yongxin Deng , Xihe Qiu , Jue Chen , Xiaoyu Tan

Post-deployment machine learning algorithms often influence the environments they act in, and thus shift the underlying dynamics that the standard reinforcement learning (RL) methods ignore. While designing optimal algorithms in this…

Machine Learning · Computer Science 2026-02-03 Debabrota Basu , Udvas Das , Brahim Driss , Uddalak Mukherjee

To ensure that large language model (LLM) responses are helpful and non-toxic, a reward model trained on human preference data is usually used. LLM responses with high rewards are then selected through best-of-$n$ (BoN) sampling or the LLM…

Machine Learning · Computer Science 2024-07-04 Adam X. Yang , Maxime Robeyns , Thomas Coste , Zhengyan Shi , Jun Wang , Haitham Bou-Ammar , Laurence Aitchison

During initial iterations of training in most Reinforcement Learning (RL) algorithms, agents perform a significant number of random exploratory steps. In the real world, this can limit the practicality of these algorithms as it can lead to…

Machine Learning · Computer Science 2022-10-17 Ashish Kumar Jayant , Shalabh Bhatnagar