arXiv research

A new algorithm for deep Q-learning with robustness to state transition uncertainty.

Improved simulation of phase transitions using hierarchical autoregressive networks.

RRPI improves offline RL by optimizing policies against worst-case dynamics.

The paper tackles robust control for insurance contracts under uncertain transition rates.

Regularization helps resolve ambiguity in mean-variance models, improving predictive uncertainty quantification.

This paper presents several models addressing optimal portfolio choice, optimal portfolio liquidation, and optimal portfolio transition issues, in which the expected returns of risky assets are unknown. Our approach is based on a coupling between Bayesian learning and dynamic programming techniques that leads to partia…

Proposes a method to enhance exploration in RL using temporal difference uncertainties.

Develops a deterministic method to approximate NSDEs for better uncertainty quantification.

Robots can rapidly acquire new skills from demonstrations. However, during generalisation of skills or transitioning across fundamentally different skills, it is unclear whether the robot has the necessary knowledge to perform the task. Failing to detect missing information often leads to abrupt movements or to collisi…

Prob-GNN quantifies travel demand uncertainty with deep learning.

Study designs steering rewards for MFGs with unknown dynamics and model uncertainty.

A critical and challenging problem in reinforcement learning is how to learn the state-action value function from the experience replay buffer and simultaneously keep sample efficiency and faster convergence to a high quality solution. In prior works, transitions are uniformly sampled at random from the replay buffer o…

Study models risks for low-carbon economy in Balkan countries, focusing on shadow economy and populism.

Paper models uncertainty in electricity and gas markets to assess its impact.

Improves robust transfer learning with side information.

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

Paper proposes a new framework for robust multi-modal data fusion under uncertainty.

As part of Basel II's incremental risk charge (IRC) methodology, this paper summarizes our extensive investigations of constructing transition probability matrices (TPMs) for unsecuritized credit products in the trading book. The objective is to create monthly or quarterly TPMs with predefined sectors and ratings that …

New algorithm solves uncertain Markov decision processes using Wasserstein uncertainty.

Novel framework for risk-sensitive reinforcement learning with robustness against uncertainty.

Study online RL with mismatched dynamics, achieving sublinear regret.

A Robust Markov Decision Process (RMDP) is a sequential decision making model that accounts for uncertainty in the parameters of dynamic systems. This uncertainty introduces difficulties in learning an optimal policy, especially for environments with large state spaces. We propose two algorithms, RTD-DQN and Deep-RoK, …

Bayesian analysis reveals epistemic uncertainty as a key diagnostic for delayed generalization in in-context learning.

Model shows how financial markets can decarbonize under climate uncertainty.

Robust Markov Decision Processes (RMDPs) intend to ensure robustness with respect to changing or adversarial system behavior. In this framework, transitions are modeled as arbitrary elements of a known and properly structured uncertainty set and a robust optimal policy can be derived under the worst-case scenario. In t…

Bayesian ANN method predicts chaotic systems with uncertainty.

Paper develops a new RL method for MDPs with uncertainty, achieving better regret bounds.

The study shows how trade uncertainty affects stock-bond correlations over time.

We here present a model of the dynamics of extremism based on opinion dynamics in order to understand the circumstances which favour its emergence and development in large fractions of the general public. Our model is based on the bounded confidence hypothesis and on the evolution of initially anti-conformist agents to…

The paper stabilizes PD term structures under forecast uncertainty using a Kalman filter with an anchored observation model.

Proposes MIVI for efficient posterior estimation and design of MCMC transitions.

Risk-averse model uncertainty framework for safe reinforcement learning.

Study dynamic risk measures with distributional uncertainty using optimal transport.

The goal of system identification is to learn about underlying physics dynamics behind the time-series data. To model the probabilistic and nonparametric dynamics model, Gaussian process (GP) have been widely used; GP can estimate the uncertainty of prediction and avoid over-fitting. Traditional GPSSMs, however, are ba…

Deep state space model forecasts time series with uncertainty.

We generalize the recently proposed quantum model for the stock market by Zhang and Huang to make it consistent with the discrete nature of the stock price. In this formalism, the price of the stock and its trend satisfy the generalized uncertainty relation and the corresponding generalized Hamiltonian contains an addi…

Study values and optimizes forestry leases under risk and uncertainty.

Minimum energy paths for transitions such as atomic and/or spin rearrangements in thermalized systems are the transition paths of largest statistical weight. Such paths are frequently calculated using the nudged elastic band method, where an initial path is iteratively shifted to the nearest minimum energy path. The co…

MetaCURL tackles non-stationary MDPs with optimal dynamic regret.

Study shows sudden loss of balance in stock market networks after 2011, reducing predictability.

Robust reinforcement learning aims to produce policies that have strong guarantees even in the face of environments/transition models whose parameters have strong uncertainty. Existing work uses value-based methods and the usual primitive action setting. In this paper, we propose robust methods for learning temporally …

BCPO optimizes offline RL policies by converting uncertainty into conservative bounds.

Safe-M$^3$-UCRL learns safe policies for multi-agent systems with global constraints.

New algorithm reduces regret and constraint violation in adversarial CMDP learning.

We present an analysis of oil prices in US$ and in other major currencies that diagnoses unsustainable faster-than-exponential behavior. This supports the hypothesis that the recent oil price run-up has been amplified by speculative behavior of the type found during a bubble-like expansion. We also attempt to unravel t…

Deep learning complements OR/MS for decision-making under uncertainty.

New theorems show agents need specific internal structures to perform well under uncertainty.

Efficient RL for linear MDPs with unknown transitions.