English
Related papers

Related papers: When Maximum Entropy Misleads Policy Optimization

200 papers

In most data-scientific approaches, the principle of Maximum Entropy (MaxEnt) is used to a posteriori justify some parametric model which has been already chosen based on experience, prior knowledge or computational simplicity. In a…

Methodology · Statistics 2022-06-29 Orestis Loukas , Ho Ryun Chung

Reinforcement learning (RL) algorithms aim to balance exploiting the current best strategy with exploring new options that could lead to higher rewards. Most common RL algorithms use undirected exploration, i.e., select random sequences of…

Machine Learning · Computer Science 2025-08-01 Bhavya Sukhija , Stelian Coros , Andreas Krause , Pieter Abbeel , Carmelo Sferrazza

While most approaches to the problem of Inverse Reinforcement Learning (IRL) focus on estimating a reward function that best explains an expert agent's policy or demonstrated behavior on a control task, it is often the case that such…

Machine Learning · Computer Science 2020-05-01 Dexter R. R. Scobee , S. Shankar Sastry

Reinforcement learning (RL) has enabled machine learning models to achieve significant advances in many fields. Most recently, RL has empowered frontier language models to solve challenging math, science, and coding problems. However,…

Machine Learning · Computer Science 2025-06-30 Mihir Prabhudesai , Lili Chen , Alex Ippoliti , Katerina Fragkiadaki , Hao Liu , Deepak Pathak

Reinforcement learning is the method of choice to train models in sampling-based setups with binary outcome feedback, such as navigation, code generation, and mathematical problem solving. In such settings, models implicitly induce a…

Reinforcement learning with verifiable rewards (RLVR) has demonstrated superior performance in enhancing the reasoning capability of large language models (LLMs). However, this accuracy-oriented learning paradigm often suffers from entropy…

Artificial Intelligence · Computer Science 2026-01-19 Hongye Cao , Zhixin Bai , Ziyue Peng , Boyan Wang , Tianpei Yang , Jing Huo , Yuyao Zhang , Yang Gao

We give an interpretation of the Maximum Entropy (MaxEnt) Principle in game-theoretic terms. Based on this interpretation, we make a formal distinction between different ways of {em applying/} Maximum Entropy distributions. MaxEnt has…

Artificial Intelligence · Computer Science 2013-01-18 Peter D. Grunwald

Mixture models are an expressive hypothesis class that can approximate a rich set of policies. However, using mixture policies in the Maximum Entropy (MaxEnt) framework is not straightforward. The entropy of a mixture model is not equal to…

Machine Learning · Computer Science 2021-03-19 Nir Baram , Guy Tennenholtz , Shie Mannor

In reinforcement learning (RL), different reward functions can define the same optimal policy but result in drastically different learning performance. For some, the agent gets stuck with a suboptimal behavior, and for others, it solves the…

Machine Learning · Computer Science 2025-02-25 Grigorii Veviurko , Wendelin Böhmer , Mathijs de Weerdt

Simplified mechanistic models in ecology have been criticized for the fact that a good fit to data does not imply the mechanism is true: pattern does not equal process. In parallel, the maximum entropy principle (MaxEnt) has been applied in…

Populations and Evolution · Quantitative Biology 2017-05-02 James P. O'Dwyer , Andrew Rominger , Xiao Xiao

Despite the many recent advances in reinforcement learning (RL), the question of learning policies that robustly satisfy state constraints under unknown disturbances remains open. In this paper, we offer a new perspective on achieving…

Machine Learning · Computer Science 2025-12-23 Pierre-François Massiani , Alexander von Rohr , Lukas Haverbeck , Sebastian Trimpe

We study inverse reinforcement learning (IRL) and imitation learning (IM), the problems of recovering a reward or policy function from expert's demonstrated trajectories. We propose a new way to improve the learning process by adding a…

Machine Learning · Computer Science 2022-08-23 The Viet Bui , Tien Mai , Patrick Jaillet

Maximum entropy reinforcement learning integrates exploration into policy learning by providing additional intrinsic rewards proportional to the entropy of some distribution. In this paper, we propose a novel approach in which the intrinsic…

Machine Learning · Computer Science 2025-09-30 Adrien Bolland , Gaspard Lambrechts , Damien Ernst

Maximum entropy (MAXENT) method has a large number of applications in theoretical and applied machine learning, since it provides a convenient non-parametric tool for estimating unknown probabilities. The method is a major contribution of…

Data Analysis, Statistics and Probability · Physics 2020-12-18 A. E. Allahverdyan , N. H. Martirosyan

Recent advances in reinforcement learning have demonstrated its ability to solve hard agent-environment interaction tasks on a super-human level. However, the application of reinforcement learning methods to practical and real-world tasks…

Artificial Intelligence · Computer Science 2021-12-03 Oleg Svidchenko , Aleksei Shpilman

We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcement Learning (RL) algorithms. We specifically focus on…

Reinforcement learning (RL) is an important field of research in machine learning that is increasingly being applied to complex optimization problems in physics. In parallel, concepts from physics have contributed to important advances in…

Machine Learning · Computer Science 2023-05-11 Argenis Arriojas , Jacob Adamczyk , Stas Tiomkin , Rahul V. Kulkarni

Reinforcement learning (RL) has enabled complex reasoning abilities in large language models (LLMs). However, most RL algorithms suffer from performance saturation, preventing continued gains as RL training scales. This problem can be…

Machine Learning · Computer Science 2026-05-12 Bolian Li , Yifan Wang , Yi Ding , Anamika Lochab , Ananth Grama , Ruqi Zhang

Reinforcement learning (RL) has become a key approach for enhancing reasoning in large language models (LLMs), yet scalable training is often hindered by the rapid collapse of policy entropy, which leads to premature convergence and…

Machine Learning · Computer Science 2026-04-14 Ming Lei , Christophe Baehr

This paper aims to overcome a major obstacle in scaling RL for reasoning with LLMs, namely the collapse of policy entropy. Such phenomenon is consistently observed across vast RL runs without entropy intervention, where the policy entropy…