English
Related papers

Related papers: Enforcing KL Regularization in General Tsallis Ent…

200 papers

The recently successful Munchausen Reinforcement Learning (M-RL) features implicit Kullback-Leibler (KL) regularization by augmenting the reward function with logarithm of the current stochastic policy. Though significant improvement has…

Machine Learning · Computer Science 2022-05-17 Lingwei Zhu , Zheng Chen , Eiji Uchibe , Takamitsu Matsubara

Many policy optimization approaches in reinforcement learning incorporate a Kullback-Leilbler (KL) divergence to the previous policy, to prevent the policy from changing too quickly. This idea was initially proposed in a seminal paper on…

Machine Learning · Computer Science 2024-03-19 Lingwei Zhu , Zheng Chen , Matthew Schlegel , Martha White

Shannon entropy regularization is widely adopted in optimal control due to its ability to promote exploration and enhance robustness, e.g., maximum entropy reinforcement learning known as Soft Actor-Critic. In this paper, Tsallis entropy,…

Optimization and Control · Mathematics 2024-03-05 Yota Hashizume , Koshi Oishi , Kenji Kashima

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

In this paper, we present a new class of Markov decision processes (MDPs), called Tsallis MDPs, with Tsallis entropy maximization, which generalizes existing maximum entropy reinforcement learning (RL). A Tsallis MDP provides a unified…

Machine Learning · Computer Science 2019-02-08 Kyungjae Lee , Sungyub Kim , Sungbin Lim , Sungjoon Choi , Songhwai Oh

This paper studies the continuous-time reinforcement learning in jump-diffusion models by featuring the q-learning (the continuous-time counterpart of Q-learning) under Tsallis entropy regularization. Contrary to the Shannon entropy, the…

Optimization and Control · Mathematics 2026-02-16 Lijun Bo , Yijie Huang , Xiang Yu , Tingting Zhang

In this paper, we propose a novel maximum causal Tsallis entropy (MCTE) framework for imitation learning which can efficiently learn a sparse multi-modal policy distribution from demonstrations. We provide the full mathematical analysis of…

Machine Learning · Computer Science 2018-05-29 Kyungjae Lee , Sungjoon Choi , Songhwai Oh

Entropy regularization is a standard technique in reinforcement learning (RL) to enhance exploration, yet it yields negligible effects or even degrades performance in Large Language Models (LLMs). We attribute this failure to the cumulative…

Computation and Language · Computer Science 2026-02-04 Chao Huang , Yujing Lu , Quangang Li , Shenghe Wang , Yan Wang , Yueyang Zhang , Long Xia , Jiashu Zhao , Zhiyuan Sun , Daiting Shi , Tingwen Liu

Mainstream Test-Time Adaptation (TTA) methods for adapting vision-language models, e.g., CLIP, typically rely on Shannon Entropy (SE) at test time to measure prediction uncertainty and inconsistency. However, since CLIP has a built-in bias…

Computer Vision and Pattern Recognition · Computer Science 2026-02-13 Xiangyu Wu , Dongming Jiang , Feng Yu , Yueying Tian , Jiaqi Tang , Qing-Guo Chen , Yang Yang , Jianfeng Lu

Maximum entropy has become a mainstream off-policy reinforcement learning (RL) framework for balancing exploitation and exploration. However, two bottlenecks still limit further performance improvement: (1) non-stationary Q-value estimation…

Machine Learning · Computer Science 2025-11-18 Guojian Zhan , Likun Wang , Pengcheng Wang , Feihong Zhang , Jingliang Duan , Masayoshi Tomizuka , Shengbo Eben Li

Adversarial training is the most effective defense against adversarial attacks. The effectiveness of the adversarial attacks has been on the design of its loss function and regularization term. The most widely used loss function in…

Machine Learning · Computer Science 2025-10-08 Zhenyu Liu , Varun Ojha

This paper studies the continuous-time q-learning (the continuous time counterpart of Q-learing) for Markov switching system under Tsallis entropy regularization. We address the difficulty in traditional RL algorithms where the Tsallis…

Optimization and Control · Mathematics 2026-01-28 Minghui Zhang , Xun Li , Xin Zhang

Deep Neural Networks (DNNs) have achieved remarkable success in a variety of tasks, especially when it comes to prediction accuracy. However, in complex real-world scenarios, particularly in safety-critical applications, high accuracy alone…

Artificial Intelligence · Computer Science 2024-05-31 Han Liu , Peng Cui , Bingning Wang , Jun Zhu , Xiaolin Hu

Recent Reinforcement Learning (RL) algorithms making use of Kullback-Leibler (KL) regularization as a core component have shown outstanding performance. Yet, only little is understood theoretically about why KL regularization helps, so far.…

Machine Learning · Computer Science 2021-01-07 Nino Vieillard , Tadashi Kozuno , Bruno Scherrer , Olivier Pietquin , Rémi Munos , Matthieu Geist

We study the sparse entropy-regularized reinforcement learning (ERL) problem in which the entropy term is a special form of the Tsallis entropy. The optimal policy of this formulation is sparse, i.e.,~at each state, it has non-zero…

Artificial Intelligence · Computer Science 2018-02-13 Ofir Nachum , Yinlam Chow , Mohammad Ghavamzadeh

We propose a novel Inverse Reinforcement Learning (IRL) method that mitigates the rigidity of fixed reward structures and the limited flexibility of implicit reward regularization. Building on the Maximum Entropy IRL framework, our approach…

Machine Learning · Computer Science 2025-11-25 Adib Karimi , Mohammad Mehdi Ebadzadeh

Inverse Reinforcement Learning (IRL) aims to facilitate a learner's ability to imitate expert behavior by acquiring reward functions that explain the expert's decisions. Regularized IRL applies strongly convex regularizers to the learner's…

Machine Learning · Computer Science 2020-12-04 Wonseok Jeon , Chen-Yang Su , Paul Barde , Thang Doan , Derek Nowrouzezahrai , Joelle Pineau

Large language models (LLMs) and multimodal LLMs (MLL-Ms) excel at chain-of-thought reasoning but face distribution shift at test-time and a lack of verifiable supervision. Recent test-time reinforcement learning (TTRL) methods derive…

Computation and Language · Computer Science 2026-03-09 Jianghao Wu , Yasmeen George , Jin Ye , Yicheng Wu , Daniel F. Schmidt , Jianfei Cai

Reinforcement Learning (RL) enhances LLM reasoning, yet a paradox emerges as models scale: strong base models saturate standard benchmarks (e.g., MATH), yielding correct but homogeneous solutions. In such environments, the lack of failure…

Machine Learning · Computer Science 2026-04-21 Zhenwen Liang , Yujun Zhou , Sidi Lu , Xiangliang Zhang , Haitao Mi , Dong Yu

Recently deep reinforcement learning (DRL) has achieved outstanding success on solving many difficult and large-scale RL problems. However the high sample cost required for effective learning often makes DRL unaffordable in resource-limited…

Machine Learning · Computer Science 2018-09-06 Gang Chen , Yiming Peng , Mengjie Zhang
‹ Prev 1 2 3 10 Next ›