arXiv research

A new update rule for deep reinforcement learning reduces learning variance and variance in reference signals.

This paper analyzes how periodic and soft target updates stabilize linear Q-learning.

Bayesian neural networks update beliefs with soft evidence, improving accuracy and calibration.

A method for selecting pseudo-labeled data in semi-supervised learning using generalized Bayes and soft revision.

Many policy gradient methods are variants of Actor-Critic (AC), where a value function (critic) is learned to facilitate updating the parameterized policy (actor). The update to the actor involves a log-likelihood update weighted by the action-values, with the addition of entropy regularization for soft variants. In th…

MSLG generates soft labels to improve DNN performance on noisy datasets.

FedSGM tackles constrained federated learning with unified framework.

Pretraining reinforcement learning methods with demonstrations has been an important concept in the study of reinforcement learning since a large amount of computing power is spent on online simulations with existing reinforcement learning algorithms. Pretraining reinforcement learning remains a significant challenge i…

Soft Actor-Critic (SAC) is an off-policy actor-critic deep reinforcement learning (DRL) algorithm based on maximum entropy reinforcement learning. By combining off-policy updates with an actor-critic formulation, SAC achieves state-of-the-art performance on a range of continuous-action benchmark tasks, outperforming pr…

MODULE solves LfO problem with high sample efficiency and stability.

Paper analyzes soft tree ensembles using NTK, finding only leaf count matters.

AOPU stabilizes NN training by approximating natural gradient, improving stability and convergence.

Boosts Q-learning by using value function bounds.

The paper examines how updates to probabilistic models influence behavior based on evidence.

π-GNN learns soft permutations for graph representations, improving graph classification and regression.

Motivated by recently published methods using frequency decompositions of convolutions (e.g. Octave Convolutions), we propose a novel convolution scheme to stabilize the training and reduce the likelihood of a mode collapse. The basic idea of our approach is to split convolutional filters into additive high and low fre…

ESAC combines genetic methods with RL to improve scalability and efficiency.

We describe $k$-MLE, a fast and efficient local search algorithm for learning finite statistical mixtures of exponential families such as Gaussian mixture models. Mixture models are traditionally learned using the expectation-maximization (EM) soft clustering technique that monotonically increases the incomplete (expec…

Multiple-step lookahead policies have demonstrated high empirical competence in Reinforcement Learning, via the use of Monte Carlo Tree Search or Model Predictive Control. In a recent work \cite{efroni2018beyond}, multiple-step greedy policies and their use in vanilla Policy Iteration algorithms were proposed and analy…

Five simple soft sensor methodologies with two update conditions were compared on two experimentally-obtained datasets and one simulated dataset. The soft sensors investigated were moving window partial least squares regression (and a recursive variant), moving window random forest regression, the mean moving window of…

A new method stabilizes deep reinforcement learning by using QGraphs to retain replay memory information.

A novel method to propagate uncertainty through the soft-thresholding nonlinearity is proposed in this paper. At every layer the current distribution of the target vector is represented as a spike and slab distribution, which represents the probabilities of each variable being zero, or Gaussian-distributed. Using the p…

Employers actively look for talents having not only specific hard skills but also various soft skills. To analyze the soft skill demands on the job market, it is important to be able to detect soft skill phrases from job advertisements automatically. However, a naive matching of soft skill phrases can lead to false pos…

IDS improves RLHF by smoothing reward data, enhancing model performance.

Paper improves AIRL by enhancing policy imitation and addressing reward recovery issues.

Soft labeling impacts OOD detection in neural networks.

Developed a new thresholding method that connects soft and hard thresholding.

Algorithm learns Nash equilibria in stochastic games using entropy-regularized policies.

Soft cells fill space without gaps, derived from minimal surfaces and deformed using edge bending.

Model-free deep reinforcement learning (RL) algorithms have been demonstrated on a range of challenging decision making and control tasks. However, these methods typically suffer from two major challenges: very high sample complexity and brittle convergence properties, which necessitate meticulous hyperparameter tuning…

To ensure stability of learning, state-of-the-art generalized policy iteration algorithms augment the policy improvement step with a trust region constraint bounding the information loss. The size of the trust region is commonly determined by the Kullback-Leibler (KL) divergence, which not only captures the notion of d…

A new method removes policy optimization in adversarial imitation learning.

Proximal operators are of particular interest in optimization problems dealing with non-smooth objectives because in many practical cases they lead to optimization algorithms whose updates can be computed in closed form or very efficiently. A well-known example is the proximal operator of the vector $\ell_1$ norm, whic…

ASBART accelerates Soft BART for faster Bayesian regression.

Maximum entropy deep reinforcement learning (RL) methods have been demonstrated on a range of challenging continuous tasks. However, existing methods either suffer from severe instability when training on large off-policy data or cannot scale to tasks with very high state and action dimensionality such as 3D humanoid l…

New method improves stability of soft FQI for offline RL.

We present an algorithm for learning decision trees using stochastic gradient information as the source of supervision. In contrast to previous approaches to gradient-based tree learning, our method operates in the incremental learning setting rather than the batch learning setting, and does not make use of soft splits…

Generalizes soft noncommutative schemes to flag varieties.

Paper proposes a new loss function for conditional models using soft targets.

Introduces Soft-SVM for binary classification bridging logistic and SVM.

Deep model learns from labeled and unlabeled data for industrial soft sensing.

This paper introduces TNTK to study infinite soft tree ensembles.

Improves deep neural networks using soft labels through alternating minimization.

The paper develops a multi-unit soft sensing model for virtual flow meters that improves few-shot learning.

In this article supervised learning problems are solved using soft rule ensembles. We first review the importance sampling learning ensembles (ISLE) approach that is useful for generating hard rules. The soft rules are then obtained with logistic regression from the corresponding hard rules. In order to deal with the p…

Recently, deep learning becomes the main focus of machine learning research and has greatly impacted many important fields. However, deep learning is criticized for lack of interpretability. As a successful unsupervised model in deep learning, the autoencoder embraces a wide spectrum of applications, yet it suffers fro…

GAIT-prop derives a biologically plausible learning rule from backpropagation.

Proposes a new method for deep ensembles that improves accuracy and calibration.