English
Related papers

Related papers: StepScorer: Accelerating Reinforcement Learning wi…

200 papers

Mathematical reasoning in large language models has improved substantially with reinforcement learning using verifiable rewards, where final answers can be checked automatically and converted into reliable training signals. Most such…

Machine Learning · Computer Science 2026-04-06 Mohammad Rezaei , Jens Lehmann , Sahar Vahdati

While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications, including the fine-tuning of generative models.…

Large Language Models (LLMs) are increasingly relied upon for solving complex reasoning tasks in domains such as mathematics, logic, and multi-step question answering. A growing line of work seeks to improve reasoning quality by scaling…

Machine Learning · Computer Science 2025-08-05 Seyyed Saeid Cheshmi , Azal Ahmad Khan , Xinran Wang , Zirui Liu , Ali Anwar

Large language models (LLMs) inevitably make mistakes when performing step-by-step mathematical reasoning. Process Reward Models (PRMs) have emerged as a promising solution by evaluating each reasoning step. However, existing PRMs typically…

Computation and Language · Computer Science 2025-03-28 Shuaijie She , Junxiao Liu , Yifeng Liu , Jiajun Chen , Xin Huang , Shujian Huang

Model-based reinforcement learning (MBRL) has gained much attention for its ability to learn complex behaviors in a sample-efficient way: planning actions by generating imaginary trajectories with predicted rewards. Despite its success, we…

Machine Learning · Computer Science 2024-02-20 Vint Lee , Pieter Abbeel , Youngwoon Lee

Reward design remains a significant bottleneck in applying reinforcement learning (RL) to real-world problems. A popular alternative is reward learning, where reward functions are inferred from human feedback rather than manually specified.…

Machine Learning · Computer Science 2026-01-16 Chaitanya Kharyal , Calarina Muslimani , Matthew E. Taylor

Reinforcement Learning with Verifiable Rewards (RLVR) improves final-answer accuracy on reasoning tasks, but it does not reliably improve reasoning quality. Because outcome rewards only assess final answers, they also reward spurious…

Machine Learning · Computer Science 2026-05-19 Chenlu Ye , Zhou Yu , Ziji Zhang , Hao Chen , Narayanan Sadagopan , Jing Huang , Tong Zhang , Anurag Beniwal

Model-based next state prediction and state value prediction are slow to converge. To address these challenges, we do the following: i) Instead of a neural network, we do model-based planning using a parallel memory retrieval system (which…

Artificial Intelligence · Computer Science 2023-02-02 John Chong Min Tan , Mehul Motani

Process Reward Models (PRMs) have achieved strong results in complex reasoning, but are bottlenecked by costly process-level supervision. A widely used alternative, Monte Carlo Estimation (MCE), defines process rewards as the probability…

Computation and Language · Computer Science 2026-01-21 Bin Xie , Bingbing Xu , Xueyun Tian , Yilin Chen , Huawei Shen

Reinforcement learning (RL) has become a promising paradigm for optimizing Retrieval-Augmented Generation (RAG) in complex reasoning tasks. However, traditional outcome-based RL approaches often suffer from reward sparsity and inefficient…

Artificial Intelligence · Computer Science 2026-01-30 Zhao Wang , Ziliang Zhao , Zhicheng Dou

While recent advances have boosted LM proficiency in linguistic benchmarks, LMs consistently struggle to reason correctly on complex tasks like mathematics. We turn to Reinforcement Learning from Human Feedback (RLHF) as a method with which…

Computation and Language · Computer Science 2023-11-13 Sarah Pan , Vladislav Lialin , Sherin Muckatira , Anna Rumshisky

In performative prediction, the deployment of a predictive model triggers a shift in the data distribution. As these shifts are typically unknown ahead of time, the learner needs to deploy a model to get feedback about the distribution it…

Machine Learning · Computer Science 2022-07-19 Meena Jagadeesan , Tijana Zrnic , Celestine Mendler-Dünner

Many real-world robot learning problems, such as pick-and-place or arriving at a destination, can be seen as a problem of reaching a goal state as soon as possible. These problems, when formulated as episodic reinforcement learning tasks,…

Robotics · Computer Science 2024-07-10 Gautham Vasan , Yan Wang , Fahim Shahriar , James Bergstra , Martin Jagersand , A. Rupam Mahmood

Inference-time alignment methods have gained significant attention for their efficiency and effectiveness in aligning large language models (LLMs) with human preferences. However, existing dominant approaches using reward-guided search…

Computation and Language · Computer Science 2025-07-01 Bin Xie , Bingbing Xu , Yige Yuan , Shengmao Zhu , Huawei Shen

We explore a method for improving the performance of large language models through self-reflection and reinforcement learning. By incentivizing the model to generate better self-reflections when it answers incorrectly, we demonstrate that a…

Computation and Language · Computer Science 2025-06-02 Shelly Bensal , Umar Jamil , Christopher Bryant , Melisa Russak , Kiran Kamble , Dmytro Mozolevskyi , Muayad Ali , Waseem AlShikh

Reinforcement learning (RL) has recently proven great success in various domains. Yet, the design of the reward function requires detailed domain expertise and tedious fine-tuning to ensure that agents are able to learn the desired…

Robotics · Computer Science 2023-03-06 Murad Dawood , Nils Dengler , Jorge de Heuvel , Maren Bennewitz

Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. However, a notable limitation of PbRL is its dependency on substantial human feedback. This dependency stems…

Machine Learning · Computer Science 2024-05-30 Fengshuo Bai , Rui Zhao , Hongming Zhang , Sijia Cui , Ying Wen , Yaodong Yang , Bo Xu , Lei Han

Process Reward Models (PRMs) provide step-level feedback for reasoning, but current PRMs usually output only a single reward score for each step. Downstream methods must therefore treat imperfect step-level reward predictions as reliable…

Computation and Language · Computer Science 2026-05-18 Jinyuan Li , Langlin Huang , Chengsong Huang , Shaoyang Xu , Donghong Cai , Yuyi Yang , Wenxuan Zhang , Jiaxin Huang

A recent goal in the Reinforcement Learning (RL) framework is to choose a sequence of actions or a policy to maximize the reward collected or minimize the regret incurred in a finite time horizon. For several RL problems in operation…

Machine Learning · Computer Science 2016-08-18 K J Prabuchandran , Tejas Bodas , Theja Tulabandhula

Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefined placeholder tokens or setting the reasoning step's length…

Artificial Intelligence · Computer Science 2025-06-03 Yuliang Liu , Junjie Lu , Zhaoling Chen , Chaofeng Qu , Jason Klein Liu , Chonghan Liu , Zefan Cai , Yunhui Xia , Li Zhao , Jiang Bian , Chuheng Zhang , Wei Shen , Zhouhan Lin