arXiv research

Study shows certainty equivalent policy minimizes regret in continuous-time systems.

Study risk-sensitive reinforcement learning with optimized certainty equivalents.

Study on implied certainty equivalent rates in financial markets and electric vehicles.

We consider a model in which a trader aims to maximize expected risk-adjusted profit while trading a single security. In our model, each price change is a linear combination of observed factors, impact resulting from the trader's current and prior activity, and unpredictable random effects. The trader must learn coeffi…

New findings reveal discount regularization can be seen as a strong prior, leading to poor performance in unevenly sampled data.

Deep learning solves dynamic programming with recursive utility.

This paper shows CEM is a special case of TTM, leading to new proofs and improved sample complexity bounds.

Study risk-sensitive reinforcement learning with Lipschitz dynamic risk measures, establishing regret bounds.

We study a security threat to batch reinforcement learning and control where the attacker aims to poison the learned policy. The victim is a reinforcement learner / controller which first estimates the dynamics and the rewards from a batch data set, and then solves for the optimal policy with respect to the estimates. …

The paper develops a new approach to conditional risk measures using modular convex analysis.

CEFOL uses deep learning for dynamic programming with recursive utility.

Solves Merton's investment-consumption problem with certainty equivalent approach.

Study uses reinforcement learning to optimize portfolios under recursive utility.

This paper tackles adaptive control of unknown Markov jump systems with sample complexity and regret bounds.

Overview of risk-sensitive Markov decision processes with Optimized Certainty Equivalent.

Study risk-sensitive market making with entropy regularization for better quote control.

For incomplete preference relations that are represented by multiple priors and/or multiple -- possibly multivariate -- utility functions, we define a certainty equivalent as well as the utility buy and sell prices and indifference price bounds as set-valued functions of the claim. Furthermore, we motivate and introduc…

The paper analyzes risk estimation methods and derives bounds for OCE risk.

Introduces new performance measures using scaled utility functions.

This work uses a scalable approach to identify partially observed nonlinear systems.

Study scaling limits for option pricing in trinomial models.

Proposes a new method to rank risky investments based on Omega measure.

We consider the class of risk measures associated with optimized certainty equivalents. This class includes several popular examples, such as CV@R and monotone mean-variance. Numerical schemes are developed for the computation of these risk measures using Fourier transform methods. This leads, in particular, to a very …

New multivariate risk measures improve on univariate OCE methods.

We study the performance of the certainty equivalent controller on Linear Quadratic (LQ) control problems with unknown transition dynamics. We show that for both the fully and partially observed settings, the sub-optimality gap between the cost incurred by playing the certainty equivalent controller on the true system …

Study optimal investment decisions for diverse risk-tolerant agents.

We consider the problem of optimal risk sharing in a pool of cooperative agents. We analyze the asymptotic behavior of the certainty equivalents and risk premia associated with the Pareto optimal risk sharing contract as the pool expands. We first study this problem under expected utility preferences with an objectivel…

New robust control method for uncertain systems using bootstrapped noise.

This paper introduces new risk measures for evaluating losses with varying time horizons.

The paper studies risk-sensitive learning schemes and provides learning bounds for empirical OCE minimizers.

The paper develops robust risk measures for uncertain loss positions.

Scores measure certainty and doubt in classification predictions.

This paper studies the optimal risk-averse timing to sell a risky asset. The investor's risk preference is described by the exponential, power, or log utility. Two stochastic models are considered for the asset price -- the geometric Brownian motion and exponential Ornstein-Uhlenbeck models -- to account for, respectiv…

Improved TD learning reduces batch sampling error.

The paper improves reinforcement learning by estimating return distributions efficiently.

Submodularity is studied for convex risk measures, including Expected Shortfall.

New bounds for adaptive control in high dimensions without fixed state space.

Study task-guided exploration in linear dynamical systems, improving sample complexity.

Optimized certainty equivalents (OCEs) is a family of risk measures widely used by both practitioners and academics. This is mostly due to its tractability and the fact that it encompasses important examples, including entropic risk measures and average value at risk. In this work we consider stochastic optimal control…

Accounting for model uncertainty in risk management and option pricing leads to infinite dimensional optimization problems which are both analytically and numerically intractable. In this article we study when this hurdle can be overcome for the so-called optimized certainty equivalent risk measure (OCE) -- including t…

We study the dynamic indifference pricing with ambiguity preferences. For this, we introduce the dynamic expected utility with ambiguity via the nonlinear expectation--G-expectation, introduced by Peng (2007). We also study the risk aversion and certainty equivalent for the agents with ambiguity. We obtain the dynamic …

We present a simulation-and-regression method for solving dynamic portfolio allocation problems in the presence of general transaction costs, liquidity costs and market impacts. This method extends the classical least squares Monte Carlo algorithm to incorporate switching costs, corresponding to transaction costs and t…

New method for dynamic valuation in markets with random endowments.

This paper tackles over-certainty in test-time adaptation models, proposing a solution to improve calibration.

The effectiveness of model-based versus model-free methods is a long-standing question in reinforcement learning (RL). Motivated by recent empirical success of RL on continuous control tasks, we study the sample complexity of popular model-based and model-free algorithms on the Linear Quadratic Regulator (LQR). We show…

We consider families of strongly consistent multivariate conditional risk measures. We show that under strong consistency these families admit a decomposition into a conditional aggregation function and a univariate conditional risk measure as introduced Hoffmann et al. (2016). Further, in analogy to the univariate cas…

We consider the optimal investment problem when the traded asset may default, causing a jump in its price. For an investor with constant absolute risk aversion, we compute indifference prices for defaultable bonds, as well as a price for dynamic protection against default. For the latter problem, our work complements S…

We propose directed time series regression, a new approach to estimating parameters of time-series models for use in certainty equivalent model predictive control. The approach combines merits of least squares regression and empirical optimization. Through a computational study involving a stochastic version of a well …