English
Related papers

Related papers: An Alternative Softmax Operator for Reinforcement …

200 papers

The softmax function is a widely used activation function in the output layers of neural networks, responsible for converting raw scores into class probabilities while introducing essential non-linearity. Implementing Softmax efficiently…

The softmax function is a ubiquitous component at the output of neural networks and increasingly in intermediate layers as well. This paper provides convex lower bounds and concave upper bounds on the softmax function, which are compatible…

Machine Learning · Computer Science 2023-03-06 Dennis Wei , Haoze Wu , Min Wu , Pin-Yu Chen , Clark Barrett , Eitan Farchi

Soft Q-learning is a variation of Q-learning designed to solve entropy regularized Markov decision problems where an agent aims to maximize the entropy regularized value function. Despite its empirical success, there have been limited…

Machine Learning · Computer Science 2024-09-06 Narim Jeong , Donghwan Lee

In reinforcement learning, the softmax parametrization is the standard approach for policies over discrete action spaces. However, it fails to capture the order relationship between actions. Motivated by a real-world industrial problem, we…

Machine Learning · Computer Science 2025-06-24 Simón Weinberger , Jairo Cugliari

The Bellman equation and its continuous form, the Hamilton-Jacobi-Bellman equation, are ubiquitous in reinforcement learning and control theory. However, these equations become intractable for high-dimensional or nonlinear systems. This…

Artificial Intelligence · Computer Science 2026-05-04 Preston Rozwood , Edward Mehrez , Ludger Paehler , Wen Sun , Steven L. Brunton

We illustrate the detrimental effect, such as overconfident decisions, that exponential behavior can have in methods like classical LDA and logistic regression. We then show how polynomiality can remedy the situation. This, among others,…

Machine Learning · Computer Science 2022-03-25 Ziqi Wang , Marco Loog

Estimating optimal dynamic policies from offline data is a fundamental problem in dynamic decision making. In the context of causal inference, the problem is known as estimating the optimal dynamic treatment regime. Even though there exists…

Econometrics · Economics 2023-12-15 Qizhao Chen , Morgane Austern , Vasilis Syrgkanis

Singular learning models with non-positive Fisher information matrices include neural networks, reduced-rank regression, Boltzmann machines, normal mixture models, and others. These models have been widely used in the development of…

Machine Learning · Statistics 2025-02-12 Miki Aoyagi

Distributional reinforcement learning algorithms have attempted to utilize estimated uncertainty for exploration, such as optimism in the face of uncertainty. However, using the estimated variance for optimistic exploration may cause biased…

Machine Learning · Computer Science 2023-12-06 Taehyun Cho , Seungyub Han , Heesoo Lee , Kyungjae Lee , Jungwoo Lee

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces noisy probability distribution, which can impair effective…

Computation and Language · Computer Science 2025-11-11 Dhananjay Ram , Wei Xia , Stefano Soatto

Recent neural network and language models rely on softmax distributions with an extremely large number of categories. Since calculating the softmax normalizing constant in this context is prohibitively expensive, there is a growing…

Machine Learning · Statistics 2018-03-26 Francois Fagan , Garud Iyengar

Evaluating the log-sum-exp function or the softmax function is a key step in many modern data science algorithms, notably in inference and classification. Because of the exponentials that these functions contain, the evaluation is prone to…

Numerical Analysis · Mathematics 2019-09-10 Pierre Blanchard , Desmond J. Higham , Nicholas J. Higham

The majority of machine learning methods can be regarded as the minimization of an unavailable risk function. To optimize the latter, given samples provided in a streaming fashion, we define a general stochastic Newton algorithm and its…

Statistics Theory · Mathematics 2023-06-30 Claire Boyer , Antoine Godichon-Baggioni

We propose a method for learning expressive energy-based policies for continuous states and actions, which has been feasible only in tabular domains before. We apply our method to learning maximum entropy policies, resulting into a new…

Machine Learning · Computer Science 2017-07-25 Tuomas Haarnoja , Haoran Tang , Pieter Abbeel , Sergey Levine

Soft actor-critic (SAC) is a popular algorithm for max-entropy reinforcement learning. In practice, the energy-based policies in SAC are often approximated using simple policy classes for efficiency, sacrificing the expressiveness and…

Machine Learning · Computer Science 2026-01-01 Yuyang Zhang , Yang Hu , Bo Dai , Na Li

In deep reinforcement learning, policy optimization methods need to deal with issues such as function approximation and the reuse of off-policy data. Standard policy gradient methods do not handle off-policy data well, leading to premature…

Machine Learning · Computer Science 2025-01-28 Qing Wang , Yingru Li , Jiechao Xiong , Tong Zhang

With an eye towards human-centered automation, we contribute to the development of a systematic means to infer features of human decision-making from behavioral data. Motivated by the common use of softmax selection in models of human…

Optimization and Control · Mathematics 2015-09-01 Paul Reverdy , Naomi E. Leonard

ASR systems are deployed across diverse environments, each with specific hardware constraints. We use supernet training to jointly train multiple encoders of varying sizes, enabling dynamic model size adjustment to fit hardware constraints…

Computation and Language · Computer Science 2025-02-05 Jingjing Xu , Eugen Beck , Zijian Yang , Ralf Schlüter

This paper questions whether the strong performance of softmax attention in transformers stems from producing a probability distribution over inputs. Instead, we argue that softmax's effectiveness lies in its implicit regularization of the…

Machine Learning · Computer Science 2026-03-16 Hemanth Saratchandran , Jianqiao Zheng , Yiping Ji , Wenbo Zhang , Simon Lucey

Algorithms for the Multi-Armed Bandit (MAB) problem play a central role in sequential decision-making and have been extensively explored both theoretically and numerically. While most classical approaches aim to identify the arm with the…

Machine Learning · Computer Science 2026-04-02 Gabriel Turinici