arXiv research

We tackle linear bandits with partially observable features, achieving sublinear regret.

DPFRL uses particle filters for decision making with complex visual observations.

Linear recurrent networks explain reinforcement learning performance in partially observable settings.

Animals need to devise strategies to maximize returns while interacting with their environment based on incoming noisy sensory observations. Task-relevant states, such as the agent's location within an environment or the presence of a predator, are often not directly observable but must be inferred using available sens…

Algorithm improves decision-making with partially observed contexts using pretrained models.

In recent years, a large amount of model-agnostic methods to improve the transparency, trustability and interpretability of machine learning models have been developed. We introduce local feature importance as a local version of a recent model-agnostic global feature importance method. Based on local feature importance…

Study efficient reinforcement learning for partially observed systems with linear structure.

New framework for reinforcement learning with sporadic state observations.

The paper develops a method to learn navigation costs from expert demonstrations in partially observable environments.

Proposes MGPLL for PL learning with non-random noise.

GADGET framework decomposes global feature effects using recursive partitioning.

Intelligent agents can cope with sensory-rich environments by learning task-agnostic state abstractions. In this paper, we propose an algorithm to approximate causal states, which are the coarsest partition of the joint history of actions and observations in partially-observable Markov decision processes (POMDP). Our m…

Paper analyzes history-based RL methods for MDPs, introduces a theoretical framework and practical algorithm.

Enhances forecasting of complex systems using FKMD.

Paper studies CLO with partial feedback, improving decision-making in uncertain contexts.

In model-based reinforcement learning, generative and temporal models of environments can be leveraged to boost agent performance, either by tuning the agent's representations during training or via use as part of an explicit planning mechanism. However, their application in practice has been limited to simplistic envi…

This paper studies the question of filtering and maximizing terminal wealth from expected utility in a partially information stochastic volatility models. The special features is that the only information available to the investor is the one generated by the asset prices, and the unobservable processes will be modeled …

Theoretical analysis of MCR for improving imputation quality in partially observed data.

Study on estimating sparse transition matrix of partially-observed VAR with noisy and sparse data.

We investigate a classification problem using multiple mobile agents capable of collecting (partial) pose-dependent observations of an unknown environment. The objective is to classify an image over a finite time horizon. We propose a network architecture on how agents should form a local belief, take local actions, an…

New methods interpret clustering outcomes without altering data structure.

Efficient RL in large POMDPs with latent determinism and embeddings.

New algorithm improves reinforcement learning from partial observations.

EDICT learns evidential distributions for irregular time series, improving predictions and uncertainty quantification.

Efficient RL in partially observable risk-sensitive environments with hindsight observations.

A new tree-based estimator, FastPD, efficiently estimates PD functions for machine learning models.

We characterize value functions in partially observable MDPs as semi-algebraic sets.

New method uses models from regularity structures as features in machine learning.

New partial models correct for confounding effects in reinforcement learning.

In this paper, we propose a new wrapper feature selection approach with partially labeled training examples where unlabeled observations are pseudo-labeled using the predictions of an initial classifier trained on the labeled training set. The wrapper is composed of a genetic algorithm for proposing new feature subsets…

New framework learns policies for partially observable systems.

RL struggles with generalization due to implicit partial observability.

ETC learns minimal representations for reinforcement learning in POMDPs.

Proposes a method to quantify and decompose disparity in ML models, separating exempt and non-exempt components.

New method selects direct causal parents from large sets of variables.

PCBM improves neural network generalization by partially observing concepts.

Paper proposes PMformer for better cryptocurrency price forecasting.

As machine learning is increasingly used to make real-world decisions, recent research efforts aim to define and ensure fairness in algorithmic decision making. Existing methods often assume a fixed set of observable features to define individuals, but lack a discussion of certain features not being observed at test ti…

Study optimal policy regret in partially observable Markov games with adaptive opponents.

A new approach uses partial likelihood to improve tree-based density estimation and inference.

Infinite BART model selects number of trees and allows different functions for clusters.

Algorithm reduces regret in partially observable systems by learning dynamics and using optimistic control.

The paper develops algorithms for competitive RL in partially observable MGs.

New PINN architectures learn high-frequency features using Fourier features.

RLHF fails when humans only partially observe, leading to inflated or overjustified feedback.

New BED method handles online inference for partially observed dynamical systems.

In reinforcement learning algorithms, leveraging multiple views of the environment can improve the learning of complicated policies. In multi-view environments, due to the fact that the views may frequently suffer from partial observability, their level of importance are often different. In this paper, we propose a dee…

This paper proposes a model of information cascades as directed spanning trees (DSTs) over observed documents. In addition, we propose a contrastive training procedure that exploits partial temporal ordering of node infections in lieu of labeled training links. This combination of model and unsupervised training makes …