arXiv research

Algorithm learns from offline data to improve performance in target environment.

LEADS improves model generalization across different environments.

New method uses unlabeled data to improve model robustness across different environments.

UAED discovers adaptive environments for robust learning.

Study on estimating causal effects with limited data and multiple environments.

Meta-learners estimate CATE from multiple environments with partial identification.

Bayesian Invariant Prediction models stable features from multi-environment data.

In Business Intelligence, accurate predictive modeling is the key for providing adaptive decisions. We studied predictive modeling problems in this research which was motivated by real-world cases that Microsoft data scientists encountered while dealing with e-commerce transaction fraud control decisions using transact…

Reinforcement learning aims at searching the best policy model for decision making, and has been shown powerful for sequential recommendations. The training of the policy by reinforcement learning, however, is placed in an environment. In many real-world applications, however, the policy training in the real environmen…

New algorithm guarantees domain generalization with few environments.

New method learns robust representations by modeling environment variation.

Estimator improves prediction with missing data in multi-environment settings.

XRM discovers environments without human annotations for OOD methods.

Mixreg improves RL generalization by mixing diverse training environments.

In many situations, we need to build and deploy separate models in related environments with different data qualities. For example, an environment with strong observation equipments (e.g., intensive care units) often provides high-quality multi-modal data, which are acquired from multiple sensory devices and have rich-…

Study binary choice with asymmetric loss, offering simple solutions.

FinRL-Meta offers market environments and benchmarks for financial reinforcement learning.

We present the use of the fitted Q iteration in algorithmic trading. We show that the fitted Q iteration helps alleviate the dimension problem that the basic Q-learning algorithm faces in application to trading. Furthermore, we introduce a procedure including model fitting and data simulation to enrich training data as…

FinRL-Meta creates diverse market environments for DRL in finance.

BAM integrates new data while selectively remembering past observations.

Inverse reinforcement learning has proved its ability to explain state-action trajectories of expert agents by recovering their underlying reward functions in increasingly challenging environments. Recent advances in adversarial learning have allowed extending inverse RL to applications with non-stationary environment …

Detect hidden confounding in observational data using multiple environments.

Research shows collective learning across diverse environments is hard due to privacy and security concerns.

CHEER boosts poor models using rich model knowledge.

HySRL improves RL sample efficiency with shifted-dynamics data.

Researchers use DT to transfer policies from one environment to another using causal reasoning.

Federated multi-mini-batch improves efficiency in non-IID environments.

Novel framework for data sharing and coordinated exploration in concurrent RL with non-identical environments.

Proposes a method to learn policies from offline data with reduced bias.

GALA framework learns invariant graph representations via environment augmentation with minimal assumptions.

A framework for learning disentangled representations of symmetric environments.

Paper tackles noise-robust domain adaptation in noisy environments.

The paper formalizes robot environments using topological concepts.

CEA augments reinforcement learning by generating counterfactual experiences.

A machine learning environment for detecting autonomous vehicle corner cases.

While machine learning is rapidly being developed and deployed in health settings such as influenza prediction, there are critical challenges in using data from one environment in another due to variability in features; even within disease labels there can be differences (e.g. "fever" may mean something different repor…

GIB improves neural network generalization by dynamically selecting task-relevant features across different sequential environments.

Unified AI system for data quality control and governance in regulated environments.

Optimization algorithm CoCo improves causal inference from diverse data.

Bayesian segmentation and uncertainty estimation improve 3D model accuracy for factory planning.

In this paper, we exploit minimal sensing information gathered from biologically inspired sensor networks to perform exploration and mapping in an unknown environment. A probabilistic motion model of mobile sensing nodes, inspired by motion characteristics of cockroaches, is utilized to extract weak encounter informati…

New method for ancestral inference in branching processes with random environments.

Autoencoder neural networks reconstruct missing indoor environment data.

This thesis improves OCO algorithms for dynamic data environments.

Proposes a method to adapt models in nonstationary environments using ℓ1 regularization.

When agents interact with a complex environment, they must form and maintain beliefs about the relevant aspects of that environment. We propose a way to efficiently train expressive generative models in complex environments. We show that a predictive algorithm with an expressive generative model can form stable belief-…

The study questions the necessity of accurate models in MBRL.

Paper argues context equals environment, improving AI generalization.