arXiv research

Improved SAC with AWMP for better control tasks.

DG improves policy gradients by weighting actions with a sigmoid of advantage and surprisal.

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 the proposed framework. First, the optimal solution of an MCTE problem is shown …

Real-world tasks are often highly structured. Hierarchical reinforcement learning (HRL) has attracted research interest as an approach for leveraging the hierarchical structure of a given task in reinforcement learning (RL). However, identifying the hierarchical policy structure that enhances the performance of RL is n…

New approach optimizes policies in adversarial MDPs using adversarial learning.

A new framework for robust policy learning in MDPs with linear mixture dynamics.

In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that uses standard supervised learning methods as subroutines. Our goal is an algorithm that utilizes only simple and convergent maximum likelihood loss functions, while also being able to leverage off-policy data. Our proposed appr…

DG separates successes and failures by gating updates with advantage and surprisal.

DGMM improves Gaussian mixture modeling efficiency and stability.

Improved RCPs for MABs using normalized weight functions.

A novel approach for safe offline RL using latent safety constraints.

Enhances mixture models with classifier-defined weights.

A new method for density estimation using nearest neighbor Dirichlet mixtures.

New framework shifts bandit algorithms from expected reward to preference metrics, optimizing mixtures of arms.

Policy gradient based reinforcement learning algorithms coupled with neural networks have shown success in learning complex policies in the model free continuous action space control setting. However, explicitly parameterized policies are limited by the scope of the chosen parametric probability distribution. We show t…

Estimates Gaussian mixtures from weighted samples efficiently.

Diffusion models accurately recover mixture weights from generated samples despite score function insensitivity.

Corrupting the input and hidden layers of deep neural networks (DNNs) with multiplicative noise, often drawn from the Bernoulli distribution (or 'dropout'), provides regularization that has significantly contributed to deep learning's success. However, understanding how multiplicative corruptions prevent overfitting ha…

Paper proposes interpretable RL policies from a mixture of experts.

Study on autoencoder denoising in high dimensions.

Proposes a Riemannian optimization for policy improvement in MDPs.

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…

OTSS learns personalized decision weights from logged decisions and outputs.

New methods improve LLM preference optimization by intelligently weighting multiple reference models.

New estimator reduces variance in off-policy evaluation for contextual bandits.

Study improves stock price prediction using adaptive Mixture of Experts framework.

New approach for pricing evaluation improves on existing methods.

Classifier ensembles are pattern recognition structures composed of a set of classification algorithms (members), organized in a parallel way, and a combination method with the aim of increasing the classification accuracy of a classification system. In this study, we investigate the application of a generalized mixtur…

Variational Proximal Policy Optimization improves reinforcement learning from human feedback.

Bayesian Parametric Portfolio Policies corrects overestimation of utility and risk in traditional PPP.

Estimates causal effects using neural networks for balancing covariates.

Reinforcement learning improves online matching by combining expert policies.

A new model predicts multivariate regression using similarities to data points.

Low-rank matrix factorization (LRMF) has received much popularity owing to its successful applications in both computer vision and data mining. By assuming noise to come from a Gaussian, Laplace or mixture of Gaussian distributions, significant efforts have been made on optimizing the (weighted) $L_1$ or $L_2$-norm los…

DNN policies improve stochastic AC OPF for power grid optimization.

Model-based clustering imposes a finite mixture modelling structure on data for clustering. Finite mixture models assume that the population is a convex combination of a finite number of densities, the distribution within each population is a basic assumption of each particular model. Among all distributions that have …

The paper tackles robust policy learning from multiple data sources.

Policy gradient is an efficient technique for improving a policy in a reinforcement learning setting. However, vanilla online variants are on-policy only and not able to take advantage of off-policy data. In this paper we describe a new technique that combines policy gradient with off-policy Q-learning, drawing experie…

New concept of mixture complexity helps detect gradual clustering changes.

This paper improves Q-learning bounds using reference-advantage decomposition.

We introduce a copula mixture model to perform dependency-seeking clustering when co-occurring samples from different data sources are available. The model takes advantage of the great flexibility offered by the copulas framework to extend mixtures of Canonical Correlation Analysis to multivariate data with arbitrary c…

The paper proposes a structure learning model for efficient reinforcement learning.

The normalized maximized likelihood (NML) provides the minimax regret solution in universal data compression, gambling, and prediction, and it plays an essential role in the minimum description length (MDL) method of statistical modeling and estimation. Here we show that the normalized maximum likelihood has a Bayes-li…

New algorithm tackles adversarial RL without horizon constraints.

We study the problem of learning policy of an infinite-horizon, discounted cost, Markov decision process (MDP) with a large number of states. We compute the actions of a policy that is nearly as good as a policy chosen by a suitable oracle from a given mixture policy class characterized by the convex hull of a set of k…

Learning policies on data synthesized by models can in principle quench the thirst of reinforcement learning algorithms for large amounts of real experience, which is often costly to acquire. However, simulating plausible experience de novo is a hard problem for many complex environments, often resulting in biases for …

New algorithm for learning mixtures with mostly uniform weights, improving on previous bounds.

Paper proposes a method to improve off-policy reinforcement learning in batch settings.