arXiv research

Novel framework for risk-sensitive reinforcement learning using martingale decomposition.

New RL agent learns sparse rewards efficiently.

New algorithm for reinforcement learning in uncertain environments with unknown thresholds.

Algorithm learns optimal coordination for strategic agents in uncertain settings.

Improved DPO framework penalizes preference uncertainty to avoid overoptimization.

The question of how to explore, i.e., take actions with uncertain outcomes to learn about possible future rewards, is a key question in reinforcement learning (RL). Here, we show a surprising result: We show that Q-learning with nonlinear Q-function and no explicit exploration (i.e., a purely greedy policy) can learn s…

In this paper we consider stochastic optimization problems for an ambiguity averse decision maker who is uncertain about the parameters of the underlying process. In a first part we consider problems of optimal stopping under drift ambiguity for one-dimensional diffusion processes. Analogously to the case of ordinary o…

The paper explores how to handle uncertain evidence in probabilistic models.

New method calculates Shapley values for uncertain functions.

A new policy learning method allows policies to abstain when uncertain, improving safety and applicability.

In this paper, within the framework of uncertainty theory, the valuation of equity warrants is investigated. Different from the methods of probability theory, the equity warrants pricing problem is solved by using the method of uncertain calculus. Based on the assumption that the firm price follows an uncertain differe…

New strategies improve multi-agent decision-making on irregular networks.

Algorithm identifies optimal stable matching in uncertain two-sided markets.

Quantum methods model uncertain volatility in financial markets.

New model predicts dynamic volatility in uncertain financial markets.

The target of this paper is to consider model the risky asset price on the financial market under the Knightian uncertainty, and pricing the ask and bid prices of the uncertain risk. We use the nonlinear analysis tool, i.e., G-frame work [26], to construct the model of the risky asset price and bid-ask pricing for the …

Study calculates Bayes risk for semi-supervised learning with uncertain labels.

New algorithm for uncertain time series classification.

New algorithm DUSA minimizes regret in structured bandits with structural information.

We present a formal model of human decision-making in explore-exploit tasks using the context of multi-armed bandit problems, where the decision-maker must choose among multiple options with uncertain rewards. We address the standard multi-armed bandit problem, the multi-armed bandit problem with transition costs, and …

Framework for robust control in cooperative systems with uncertain common noise.

This thesis proposes a derivatives hedging framework using deep learning and reinforcement learning.

This paper analyzes the multi-armed bandit model using path-integral methods.

A method for accurate pricing of multidimensional derivatives under uncertain volatility.

The paper addresses portfolio allocation with uncertain covariance matrices, finding a logarithmic risk dependence.

Develops new methods for risk-aware decision-making in medical bandits.

Bayesian Gaussian process models handle uncertain data locations in PDE approximations.

Polynomial chaos surrogates quantify epistemic uncertainty in AI-driven scientific models.

Framework for games with uncertain parameters, ensuring no player can improve by changing strategy.

Model quantifies uncertainty's impact on European option prices.

IDT learns human preferences from uncertain decisions, even when humans are suboptimal.

The paper tackles robust control with uncertain dependence using data-driven methods.

Reinforcement Learning (RL) has demonstrated a great potential for automatically solving decision-making problems in complex uncertain environments. RL proposes a computational approach that allows learning through interaction in an environment with stochastic behavior, where agents take actions to maximize some cumula…

Paper proposes online optimization for uncertain systems using machine learning and DRO.

This paper optimizes sampling policies for Bayesian optimization to improve exploration and exploitation.

This paper tackles JSSP with uncertain task durations using DRL.

The broad set of deep generative models (DGMs) has achieved remarkable advances. However, it is often difficult to incorporate rich structured domain knowledge with the end-to-end DGMs. Posterior regularization (PR) offers a principled framework to impose structured constraints on probabilistic models, but has limited …

This paper first describes a class of uncertain stochastic control systems with Markovian switching, and derives an Itô-Liu formula for Markov-modulated processes. And we characterize an optimal control law, which satisfies the generalized Hamilton-Jacobi-Bellman (HJB) equation with Markovian switching. Then, by using …

This paper improves learning uncertain Bayesian networks from incomplete data.

Proposes a new uncertain volatility model with worst-case scenario analysis.

In this paper, we propose the uncertain volatility models with stochastic bounds. Like the regular uncertain volatility models, we know only that the true model lies in a family of progressively measurable and bounded processes, but instead of using two deterministic bounds, the uncertain volatility fluctuates between …

UnKGCP generates prediction intervals for uncertain knowledge graphs with statistical guarantees.

AIRBO optimizes robustly under uncertain inputs.

Novel pricing method for equity-indexed annuities under uncertain volatility and stochastic interest rate.

GPMI method interpolates uncertain atrial conduction velocity on non-Euclidean manifolds.

A machine learning approach to compute Black-Scholes prices with uncertain volatility.

Diffusion approximations optimize sequential experimentation for uncertain parameters.

The paper tackles mean-variance analysis in Bayesian optimization under uncertainty.