arXiv research

Optimistic algorithm reduces regret and constraint violations in online convex optimization with adversarial constraints.

Paper tackles constrained bandit problems with a new learning framework.

Paper tackles online DR-submodular maximization with stochastic constraints.

The paper calculates bounds for risk metrics and entropies under partial information constraints.

In this work we consider adversarial contextual bandits with risk constraints. At each round, nature prepares a context, a cost for each arm, and additionally a risk for each arm. The learner leverages the context to pull an arm and then receives the corresponding cost and risk associated with the pulled arm. In additi…

LinConTS improves regret and constraint violations in probabilistic linearly constrained bandits.

In this paper, we study reinforcement learning (RL) algorithms to solve real-world decision problems with the objective of maximizing the long-term reward as well as satisfying cumulative constraints. We propose a novel first-order policy optimization method, Interior-point Policy Optimization (IPO), which augments the…

New algorithms for efficient causal interventions with budget constraints and without constraints.

New algorithm reduces constraint violation to $O(T^{1/3})$ while maintaining $O(\sqrt{T})$ regret.

Controller-Augmented Hidden Markov Models (CHMMs) are a framework for constrained sequential inference.

We present an adaptive online gradient descent algorithm to solve online convex optimization problems with long-term constraints , which are constraints that need to be satisfied when accumulated over a finite number of rounds T , but can be violated in intermediate rounds. For some user-defined trade-off parameter $β$…

In this article, inspired by Shi, et al. we investigate the optimal portfolio selection with one risk-free asset and one risky asset in a multiple period setting under cumulative prospect theory (CPT). Compared with their study, our novelty is that we consider a stochastic benchmark, and portfolio constraints. We test …

A novel approach for safe offline RL using latent safety constraints.

New method calibrates classifier probabilities with guaranteed coverage.

New RL approach tackles constrained Markov decision processes.

New framework finds periodic policies in reset-free MDPs with sublinear regret.

Optimizes portfolios using CPT utility via convex optimization.

New method reduces total cost constraints in CBwK to sqrt(T) with fairness application.

New approach tackles resource constraints in bandit problems with weakly adaptive algorithms.

UCRL-CMDP algorithm optimizes RL with constraints on average costs.

Method determines credit transition matrix from cumulative default probabilities.

The objective in a traditional reinforcement learning (RL) problem is to find a policy that optimizes the expected value of a performance metric such as the infinite-horizon cumulative discounted or long-run average cost/reward. In practice, optimizing the expected value alone may not be satisfactory, in that it may be…

SEEDA optimizes dose allocation in clinical trials to balance efficacy and safety.

New method tackles safe reinforcement learning from offline data.

We treat a fairly broad class of financial models which includes markets with proportional transaction costs. We consider an investor with cumulative prospect theory preferences and a non-negativity constraint on portfolio wealth. The existence of an optimal strategy is shown in this context in a class of generalized s…

PDCA algorithm learns policies for RL with constraints using a primal-dual approach.

New algorithm optimizes online network resource allocation with long-term constraints.

This paper optimizes multi-channel sequential advertising to maximize cumulative revenue.

Algorithm maximizes user rewards under per-item budget constraints.

The paper optimizes stock portfolios with constraints based on performance attribution.

Exponential dispersion model is a useful framework in machine learning and statistics. Primarily, thanks to the additive structure of the model, it can be achieved without difficulty to estimate parameters including mean. However, tight conditions on cumulant function, such as analyticity, strict convexity, and steepne…

Optimal dividend strategy with irreversible reinsurance constraints.

Optimal bounds on regret and constraint violation in adversarial COCO.

FISAR uses neural networks to optimize safe reinforcement learning with forward-invariant constraints.

A new RL method handles uncertainty and constraints in real-time optimization.

We consider online optimization in the 1-lookahead setting, where the objective does not decompose additively over the rounds of the online game. The resulting formulation enables us to deal with non-stationary and/or long-term constraints , which arise, for example, in online display advertising problems. We propose a…

New algorithms for constrained online optimization with memory and predictions.

Improved COCO algorithms with better constraint control.

This paper studies the optimal dividend problem with capital injection under the constraint that the cumulative dividend strategy is absolutely continuous. We consider an open problem of the general spectrally negative case and derive the optimal solution explicitly using the fluctuation identities of the refracted-ref…

A new model uses neural networks to efficiently learn multivariate temporal point processes.

Novel method for efficient optimization of noisy, expensive hybrid models.

A decentralized algorithm minimizes cumulative regret in stochastic linear bandits with safety constraints.

Optimal bidding strategy for multi-platform ad auctions under budget constraints.

While most approaches to the problem of Inverse Reinforcement Learning (IRL) focus on estimating a reward function that best explains an expert agent's policy or demonstrated behavior on a control task, it is often the case that such behavior is more succinctly represented by a simple reward combined with a set of hard…

This paper studies the impact of limited switches on resource-constrained dynamic pricing with demand learning. We focus on the classical price-based blind network revenue management problem and extend our results to the bandits with knapsacks problem. In both settings, a decision maker faces stochastic and distributio…

Paper tackles robust MDPs with sample complexity guarantees.

Geometric analysis of ROC and PR curves for binary classification.

New algorithm reduces regret and constraint violation in online convex optimization with complex constraints.