arXiv research

Regularized greedy policies outperform classical greedy in finite-horizon bandit problems.

The paper analyzes NPG in finite-horizon MDPs and provides convergence guarantees.

We investigate the growth optimal strategy over a finite time horizon for a stock and bond portfolio in an analytically solvable multiplicative Markovian market model. We show that the optimal strategy consists in holding the amount of capital invested in stocks within an interval around an ideal optimal investment. Th…

Study examines Wang-Yau quasi-local energy in strong fields near apparent horizons.

New RL method learns K-step lookahead Q-functions for fixed-horizon MDPs.

Solves expert prediction problem for 4 experts in finite time horizon.

New IS methods fail to reduce variance in long-horizon MDPs.

A new ML algorithm solves complex economic control problems.

We aim to construct the optimal solutions to the undiscounted continuous-time infinite horizon optimization problems, the objective functionals of which may be unbounded. We identify the condition under which the limit of the solutions to the finite horizon problems is optimal for the infinite horizon problems under th…

We consider generic static spacetimes with Killing horizons and study properties of curvature tensors in the horizon limit. It is determined that the Weyl, Ricci, Riemann and Einstein tensors are algebraically special and mutually aligned on the horizon. It is also pointed out that results obtained in the tetrad adjust…

Study optimal stopping problems with finite-time horizon and proves continuity and strict monotonicity of the boundary.

In this expository paper we illustrate the generality of game theoretic probability protocols of Shafer and Vovk (2001) in finite-horizon discrete games. By restricting ourselves to finite-horizon discrete games, we can explicitly describe how discrete distributions with finite support and the discrete pricing formulas…

This paper uses recent results on continuous-time finite-horizon optimal switching problems with negative switching costs to prove the existence of a saddle point in an optimal stopping (Dynkin) game. Sufficient conditions for the game's value to be continuous with respect to the time horizon are obtained using recent …

New algorithms minimize regret in SSP with optimal sparse updates.

We aim to generalize the results of Cai and Nitta (2007) by allowing both the utility and production function to depend on time. We also consider an additional intertemporal optimality criterion. We clarify the conditions under which the limit of the solutions for the finite horizon problems is optimal among all attain…

In this paper, we study optimal switching problems under ambiguity. To characterize the optimal switching under ambiguity in the finite horizon, we use multidimensional reflected backward stochastic differential equations (multidimensional RBSDEs) and show that a value function of the optimal switching under ambiguity …

Modeling risk and performance with Levy-stable distributions.

I analyse the frequentist regret of the famous Gittins index strategy for multi-armed bandits with Gaussian noise and a finite horizon. Remarkably it turns out that this approach leads to finite-time regret guarantees comparable to those available for the popular UCB algorithm. Along the way I derive finite-time bounds…

In this paper, we investigate dynamic optimization problems featuring both stochastic control and optimal stopping in a finite time horizon. The paper aims to develop new methodologies, which are significantly different from those of mixed dynamic optimal control and stopping problems in the existing literature, to stu…

Study optimal consumption with drawdown limits over a fixed time frame.

Boundary-induced risk aversion in non-ergodic growth models.

Study examines deformations of Kerr-(A)dS near horizon geometry.

New method detects black hole horizons using Lie algebra invariants.

Paper uses DRL for smart MG energy dispatch, improving stability and performance.

Study long-term asset liquidation behavior with external flows.

Boundary-induced apparent risk aversion in non-ergodic growth models.

Firms miscount their customers who stop buying without saying goodbye.

Developed LQ MFG theory with common noise, proving existence and uniqueness.

Optimal dividend strategy with capital injections over a finite time horizon.

Kernel-UCBVI algorithm balances exploration and exploitation in metric state-action spaces.

Paper analyzes convergence of dynamic policy gradient for MDPs, improving performance in finite-time problems.

We characterise the value function of the optimal dividend problem with a finite time horizon as the unique classical solution of a suitable Hamilton-Jacobi-Bellman equation. The optimal dividend strategy is realised by a Skorokhod reflection of the fund's value at a time-dependent optimal boundary. Our results are obt…

Optimal reinsurance and dividend strategy for insurance companies in a finite time.

BINOCULARS improves experimental design by balancing exploration and exploitation.

Logarithmic regret achieved in continuous-time linear-quadratic reinforcement learning.

Study on BSDEs with random time horizon, focusing on existence and properties.

Optimal purchasing policy for mean-reverting items with a finite deadline.

This paper is concerned with offline reinforcement learning (RL), which learns using pre-collected data without further exploration. Effective offline RL would be able to accommodate distribution shift and limited data coverage. However, prior algorithms or analyses either suffer from suboptimal sample complexities or …

The paper studies the question of whether the classical mirror and synchronous couplings of two Brownian motions minimise and maximise, respectively, the coupling time of the corresponding geometric Brownian motions. We establish a characterisation of the optimality of the two couplings over any finite time horizon and…

Reward tweaking optimizes behavior for long-term goals by adjusting the reward function.

We demonstrate the existence of spherically-symmetric truly naked black holes (TNBH) for which the Kretschmann scalar is finite on the horizon but some curvature components including those responsible for tidal forces as well as the energy density $\barρ$ measured by a free-falling observer are infinite. We choose a ra…

This paper concerns the numerical solution of the finite-horizon Optimal Investment problem with transaction costs under Potential Utility. The problem is initially posed in terms of an evolutive HJB equation with gradient constraints. In Finite-Horizon Optimal Investment with Transaction Costs: A Parabolic Double Obst…

Develops a regression approach for solving MDPs with general state and action spaces.

New algorithm learns optimal policies with just 1 episode, settling horizon-dependence in RL.

New algorithms improve on Thompson Sampling for multi-armed bandits with penalties.

New meta-reinforcement learning method improves performance in finite-horizon MDPs.

Combines RL and imitation learning with oracle to optimize policies.

Improved RL algorithm reduces regret in large state spaces.