English
Related papers

Related papers: On Entropy Control in LLM-RL Algorithms

200 papers

As large language models (LLMs) continue to grow in capability, so do the risks of harmful misuse through fine-tuning. While most prior studies assume that attackers rely on supervised fine-tuning (SFT) for such misuse, we systematically…

Machine Learning · Computer Science 2026-05-12 Weitao Feng , Lixu Wang , Peizhuo Lv , Tianyi Wei , Jie Zhang , Chongyang Gao , Sinong Zhan , Wei Dong

Reinforcement learning (RL) has demonstrated impressive performance in decision-making tasks like embodied control, autonomous driving and financial trading. In many decision-making tasks, the agents often encounter the problem of executing…

Machine Learning · Computer Science 2024-07-23 Jing-Cheng Pang , Tian Xu , Shengyi Jiang , Yu-Ren Liu , Yang Yu

Sampling-based model predictive control (MPC) has found significant success in optimal control problems with non-smooth system dynamics and cost function. Many machine learning-based works proposed to improve MPC by a) learning or…

Machine Learning · Computer Science 2024-01-08 Sungwook Yang , Chaoying Pei , Ran Dai , Chuangchuang Sun

Multimodal reward models are crucial for aligning multimodal large language models with human preferences. Recent works have incorporated reasoning capabilities into these models, achieving promising results. However, training these models…

Artificial Intelligence · Computer Science 2026-02-03 Shidong Yang , Tongwen Huang , Hao Wen , Yong Wang , Li Chen , Xiangxiang Chu

Recently, reinforcement learning (RL) has become a common choice in enhancing the reasoning capabilities of vision-language models (VLMs). Considering existing RL-based finetuning methods, entropy intervention turns out to be an effective…

Artificial Intelligence · Computer Science 2025-12-13 Yang Yu , Zhuangzhuang Chen , Siqi Wang , Lanqing Li , Xiaomeng Li

In reinforcement learning (RL), the ability to utilize prior knowledge from previously solved tasks can allow agents to quickly solve new problems. In some cases, these new problems may be approximately solved by composing the solutions of…

Machine Learning · Computer Science 2023-01-02 Jacob Adamczyk , Argenis Arriojas , Stas Tiomkin , Rahul V. Kulkarni

On-policy reinforcement learning (RL) algorithms are widely used for their strong asymptotic performance and training stability, but they struggle to scale with larger batch sizes, as additional parallel environments yield redundant data…

Machine Learning · Computer Science 2025-11-13 Jianren Wang , Yifan Su , Abhinav Gupta , Deepak Pathak

We aim to develop off-policy DRL algorithms that not only exceed state-of-the-art performance but are also simple and minimalistic. For standard continuous control benchmarks, Soft Actor-Critic (SAC), which employs entropy maximization,…

Machine Learning · Computer Science 2020-12-08 Che Wang , Yanqiu Wu , Quan Vuong , Keith Ross

Reinforcement learning (RL) enables sequential decision-making in complex and high-dimensional environments through interaction with the environment. In most real-world applications, however, a high number of interactions are infeasible. In…

Machine Learning · Computer Science 2024-12-17 Md Ferdous Alam , Parinaz Naghizadeh , David Hoelzle

This paper studies the constrained/safe reinforcement learning (RL) problem with sparse indicator signals for constraint violations. We propose a model-based approach to enable RL agents to effectively explore the environment with unknown…

Artificial Intelligence · Computer Science 2021-03-09 Zuxin Liu , Hongyi Zhou , Baiming Chen , Sicheng Zhong , Martial Hebert , Ding Zhao

The effect of the relative entropy asymmetry is analyzed in the empirical risk minimization with relative entropy regularization (ERM-RER) problem. A novel regularization is introduced, coined Type-II regularization, that allows for…

Information Theory · Computer Science 2023-06-13 Francisco Daunas , Iñaki Esnaola , Samir M. Perlaza , H. Vincent Poor

We propose \emph{Choquet regularizers} to measure and manage the level of exploration for reinforcement learning (RL), and reformulate the continuous-time entropy-regularized RL problem of Wang et al. (2020, JMLR, 21(198)) in which we…

Machine Learning · Statistics 2022-08-19 Xia Han , Ruodu Wang , Xun Yu Zhou

In the Bayesian reinforcement learning (RL) setting, a prior distribution over the unknown problem parameters -- the rewards and transitions -- is assumed, and a policy that optimizes the (posterior) expected return is sought. A common…

Machine Learning · Computer Science 2021-09-27 Aviv Tamar , Daniel Soudry , Ev Zisselman

Large Language Models (LLMs) are typically fine-tuned for reasoning tasks through a two-stage pipeline of Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL), a process fraught with catastrophic forgetting and suboptimal…

Machine Learning · Computer Science 2025-10-13 Lixuan He , Jie Feng , Yong Li

Modern Deep Reinforcement Learning (RL) algorithms require estimates of the maximal Q-value, which are difficult to compute in continuous domains with an infinite number of possible actions. In this work, we introduce a new update rule for…

Machine Learning · Computer Science 2023-03-02 Divyansh Garg , Joey Hejna , Matthieu Geist , Stefano Ermon

Traditional control theory-based methods require tailored engineering for each system and constant fine-tuning. In power plant control, one often needs to obtain a precise representation of the system dynamics and carefully design the…

Systems and Control · Electrical Eng. & Systems 2024-09-21 Yixuan Sun , Sami Khairy , Richard B. Vilim , Rui Hu , Akshay J. Dave

We tackle the problem of Selective Classification where the objective is to achieve the best performance on a predetermined ratio (coverage) of the dataset. Recent state-of-the-art selective methods come with architectural changes either…

Machine Learning · Computer Science 2023-03-03 Leo Feng , Mohamed Osama Ahmed , Hossein Hajimirsadeghi , Amir Abdi

Policy regularization methods such as maximum entropy regularization are widely used in reinforcement learning to improve the robustness of a learned policy. In this paper, we show how this robustness arises from hedging against worst-case…

Machine Learning · Computer Science 2024-04-29 Rob Brekelmans , Tim Genewein , Jordi Grau-Moya , Grégoire Delétang , Markus Kunesch , Shane Legg , Pedro Ortega

Large Language Models (LLMs) have made remarkable progress in enhancing step-by-step reasoning through reinforcement learning. However, the Group Relative Policy Optimization (GRPO) algorithm, which relies on sparse reward rules, often…

Artificial Intelligence · Computer Science 2025-07-30 Xingjian Zhang , Siwei Wen , Wenjun Wu , Lei Huang

In recent years, Reinforcement Learning (RL) has been applied to real-world problems with increasing success. Such applications often require to put constraints on the agent's behavior. Existing algorithms for constrained RL (CRL) rely on…

Machine Learning · Computer Science 2023-03-07 Ted Moskovitz , Brendan O'Donoghue , Vivek Veeriah , Sebastian Flennerhag , Satinder Singh , Tom Zahavy