English
Related papers

Related papers: Relative Trajectory Balance is equivalent to Trust…

200 papers

Reinforcement learning (RL) has emerged as an effective paradigm for enhancing model reasoning. However, existing RL methods like GRPO typically rely on unstructured self-sampling to fit scalar rewards, often producing inefficient rollouts…

Computation and Language · Computer Science 2026-05-18 Jinyang Wu , Chonghua Liao , Mingkuan Feng , Shuai Zhang , Zhengqi Wen , Haoran Luo , Ling Yang , Huazhe Xu , Jianhua Tao

Recurrent neural networks (RNNs) are commonly trained with the truncated backpropagation-through-time (TBPTT) algorithm. For the purposes of computational tractability, the TBPTT algorithm truncates the chain rule and calculates the…

Machine Learning · Computer Science 2025-01-15 Samuel Chun-Hei Lam , Justin Sirignano , Konstantinos Spiliopoulos

Reinforcement learning (RL) is frequently employed in fine-tuning large language models (LMs), such as GPT-3, to penalize them for undesirable features of generated sequences, such as offensiveness, social bias, harmfulness or falsehood.…

Machine Learning · Computer Science 2022-10-24 Tomasz Korbak , Ethan Perez , Christopher L Buckley

We study online transfer reinforcement learning (RL) in episodic Markov decision processes, where experience from related source tasks is available during learning on a target task. A fundamental difficulty is that task similarity is…

Machine Learning · Computer Science 2026-05-26 Elynn Chen , Enpei Zhang , Jinhang Chai , Yujun Yan

Mobility trajectories are essential for understanding urban dynamics and enhancing urban planning, yet access to such data is frequently hindered by privacy concerns. This research introduces a transformative framework for generating…

Reinforcement learning (RL) is a key post-pretraining step for aligning large language models (LLMs) with complex tasks and human preferences. While it is often assumed that RL fine-tuning requires updating most of a model's parameters, we…

Machine Learning · Computer Science 2025-07-30 Andrii Balashov

This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to optimize downstream reward functions. While diffusion models are widely known to provide excellent generative modeling capability, practical…

Machine Learning · Computer Science 2024-07-19 Masatoshi Uehara , Yulai Zhao , Tommaso Biancalani , Sergey Levine

Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning from reward signals to explicitly improve desirable aspects such as image quality and prompt…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 David McAllister , Miika Aittala , Tero Karras , Janne Hellsten , Angjoo Kanazawa , Timo Aila , Samuli Laine

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key approach for enhancing LLM reasoning. However, standard frameworks like Group Relative Policy Optimization (GRPO) typically employ a uniform rollout budget, leading…

Machine Learning · Computer Science 2026-02-09 Zhiyuan Yao , Yi-Kai Zhang , Yuxin Chen , Yueqing Sun , Zishan Xu , Yu Yang , Tianhao Hu , Qi Gu , Hui Su , Xunliang Cai

Reinforcement Learning (RL) is a method for learning decision-making tasks that could enable robots to learn and adapt to their situation on-line. For an RL algorithm to be practical for robotic control tasks, it must learn in very few…

Artificial Intelligence · Computer Science 2015-03-19 Todd Hester , Michael Quinlan , Peter Stone

Generative Flow Networks (GFlowNets) have been shown effective to generate combinatorial objects with desired properties. We here propose a new GFlowNet training framework, with policy-dependent rewards, that bridges keeping flow balance of…

Machine Learning · Computer Science 2025-06-04 Puhua Niu , Shili Wu , Mingzhou Fan , Xiaoning Qian

We present flow Q-learning (FQL), a simple and performant offline reinforcement learning (RL) method that leverages an expressive flow-matching policy to model arbitrarily complex action distributions in data. Training a flow policy with RL…

Machine Learning · Computer Science 2025-05-27 Seohong Park , Qiyang Li , Sergey Levine

Meta learning has been widely used to exploit rich-resource source tasks to improve the performance of low-resource target tasks. Unfortunately, most existing meta learning approaches treat different source tasks equally, ignoring the…

Computation and Language · Computer Science 2025-04-14 Yu Fu , Jie He , Yifan Yang , Qun Liu , Deyi Xiong

Frontier models have demonstrated exceptional capabilities following the integration of task-reward-based reinforcement learning (RL) into their training pipelines, enabling systems to evolve from pure reasoning models into sophisticated…

Machine Learning · Computer Science 2026-04-20 Sarthak Mittal , Leo Gagnon , Guillaume Lajoie

Generative flow networks (GFlowNets) are a method for learning a stochastic policy for generating compositional objects, such as graphs or strings, from a given unnormalized density by sequences of actions, where many possible action…

Machine Learning · Computer Science 2023-10-05 Nikolay Malkin , Moksh Jain , Emmanuel Bengio , Chen Sun , Yoshua Bengio

Pretraining reinforcement learning (RL) models on offline datasets is a promising way to improve their training efficiency in online tasks, but challenging due to the inherent mismatch in dynamics and behaviors across various tasks. We…

Machine Learning · Computer Science 2024-06-06 Minting Pan , Yitao Zheng , Yunbo Wang , Xiaokang Yang

Reinforcement Learning (RL) has become the de facto standard for tuning LLMs to solve tasks involving reasoning. However, growing evidence shows that models trained in such way often suffer from a significant loss in diversity. We argue…

Machine Learning · Computer Science 2026-03-09 Germán Kruszewski , Pierre Erbacher , Jos Rozen , Marc Dymetman

Reinforcement Learning (RL) is a widely employed machine learning architecture that has been applied to a variety of control problems. However, applications in safety-critical domains require a systematic and formal approach to specifying…

Machine Learning · Computer Science 2023-06-07 Hosein Hasanbeig , Daniel Kroening , Alessandro Abate

Reinforcement Learning with Verifiable Rewards (RLVR)-based post-training of Large Language Models (LLMs) has been shown to improve accuracy on reasoning tasks and continues to attract significant attention. Existing RLVR methods, however,…

Artificial Intelligence · Computer Science 2025-10-22 Soumya Rani Samineni , Durgesh Kalwar , Vardaan Gangal , Siddhant Bhambri , Subbarao Kambhampati

Merely pursuing performance may adversely affect the safety, while a conservative policy for safe exploration will degrade the performance. How to balance the safety and performance in learning-based control problems is an interesting yet…

Systems and Control · Electrical Eng. & Systems 2025-01-28 Xinyang Wang , Hongwei Zhang , Shimin Wang , Wei Xiao , Martin Guay