arXiv research

Characterizes optimal-speed quantum state evolution Hamiltonians.

We present a novel technique to solve the problem of managing optimally a pumped hydroelectric storage system. This technique relies on representing the system as a stochastic optimal control problem with state constraints, these latter corresponding to the finite volume of the reservoirs. Following the recent level-se…

Proposes a new framework for optimizing utility with state-dependent benchmarks.

Unique optimal strategy identified for state-dependent risk aversion.

Optimizes wireless network resource management with state-augmented policies.

Protocol learns pure quantum states with minimal disturbance.

Optimizes electric field to control molecule states in Hartree-Fock theory.

Bayesian approach optimizes in-context learning for state space models.

Optimal transport theory applied to quantum states on Grassmannians.

We consider 1-qubit mixed quantum state estimation by adaptively updating measurements according to previously obtained outcomes and measurement settings. Updates are determined by the average-variance-optimality (A-optimality) criterion, known in the classical theory of experimental design and applied here to quantum …

Solves optimal control for stochastic processes with absorbing states.

State-augmented algorithm optimizes wireless network resource management.

Efficiently plans large MDPs with weak function approximations.

Proposes ICC method for dynamic portfolio optimization.

Optimal estimator derived for partially observable LTI systems.

AE-LSVI identifies near-optimal policies in complex systems with minimal data.

Paper proposes method for optimal control of unknown systems with latent states.

Robust RL with learned optimal adversary improves agent performance under adversarial state observations.

Portfolio turnpikes state that, as the investment horizon increases, optimal portfolios for generic utilities converge to those of isoelastic utilities. This paper proves three kinds of turnpikes. In a general semimartingale setting, the abstract turnpike states that optimal final payoffs and portfolios converge under …

RPO uses past and future state-action info for better policy optimization.

The paper calculates optimal trading turnover in terms of asset liquidity and alpha autocorrelation.

Most decision theories, including expected utility theory, rank dependent utility theory and cumulative prospect theory, assume that investors are only interested in the distribution of returns and not in the states of the economy in which income is received. Optimal payoffs have their lowest outcomes when the economy …

Study efficient algorithms for nonconvex optimization with state-dependent Markov data.

Recurrent networks learn beliefs from history in partially observable environments.

Optimal persuasion involves projecting state vectors onto lower-dimensional 'optimal information manifolds'.

New RL method handles large state-action spaces with complex models.

Second-order optimizers retain residual information after data deletion, affecting machine unlearning.

We decode latent states in Block MDPs and learn near-optimal policies.

Solves optimal control with state constraints using probabilistic methods.

Study optimal offline RL with uncertainty sets and distribution shifts.

Generically learns movement control policies from exploration data.

We propose an algorithm for deterministic continuous Markov Decision Processes with sparse rewards that computes the optimal policy exactly with no dependency on the size of the state space. The algorithm has time complexity of $O( |R|^3 \times |A|^2 )$ and memory complexity of $O( |R| \times |A| )$, where $|R|$ is the…

Sample inefficiency is a long-lasting problem in reinforcement learning (RL). The state-of-the-art estimates the optimal action values while it usually involves an extensive search over the state-action space and unstable optimization. Towards the sample-efficient RL, we propose ranking policy gradient (RPG), a policy …

Imitation learning is a control design paradigm that seeks to learn a control policy reproducing demonstrations from expert agents. By substituting expert demonstrations for optimal behaviours, the same paradigm leads to the design of control policies closely approximating the optimal state-feedback. This approach requ…

Counterexample shows state-constrained optimal control problems can have Young measure gaps.

Novel method for shape optimization of non-smooth PDEs.

Bayesian control prepares GHZ states in Rydberg atoms.

In this paper, we introduce a novel form of value function, $Q(s, s')$, that expresses the utility of transitioning from a state $s$ to a neighboring state $s'$ and then acting optimally thereafter. In order to derive an optimal policy, we develop a forward dynamics model that learns to make next-state predictions that…

In this paper we consider an energy storage optimization problem in finite time in a model with partial information that allows for a changing economic environment. The state process consists of the storage level controlled by the storage manager and the energy price process, which is a diffusion process the drift of w…

Study designs neural networks for fault localization, state estimation, and optimal PMU placement in power systems.

This paper deals with discrete-time Markov control processes on a general state space. A long-run risk-sensitive average cost criterion is used as a performance measure. The one-step cost function is nonnegative and possibly unbounded. Using the vanishing discount factor approach, the optimality inequality and an optim…

New method prepares 3-qubit states using local gates and controlled-Z gates.

Entropy regularization is used to get improved optimization performance in reinforcement learning tasks. A common form of regularization is to maximize policy entropy to avoid premature convergence and lead to more stochastic policies for exploration through action space. However, this does not ensure exploration in th…

Hill-ADAM optimizes loss landscapes by exploring state space deterministically.

The thesis optimizes quantum state exploration using bandit algorithms.

This paper optimizes MDP policies for efficient state aggregation.

The policy gradient theorem is defined based on an objective with respect to the initial distribution over states. In the discounted case, this results in policies that are optimal for one distribution over initial states, but may not be uniformly optimal for others, no matter where the agent starts from. Furthermore, …

This paper studies a class of continuous-time scalar-state stochastic Linear-Quadratic (LQ) optimal control problem with the linear control constraints. Applying the state separation theorem induced from its special structure, we develop the explicit solution for this class of problem. The revealed optimal control poli…