Related papers: Path Planning Problems with Side Observations-When…

This paper investigates the robustness of causal bandits (CBs) in the face of temporal model fluctuations. This setting deviates from the existing literature's widely-adopted assumption of constant causal models. The focus is on causal…

We study online learning and equilibrium computation in games with polyhedral decision sets, a property shared by both normal-form games and extensive-form games (EFGs), when the learning agent is restricted to using a best-response oracle.…

Sampling-Based Optimal(SBO) path planning has been mainly used for robotic arm manipulation tasks. Several research works have been carried out in order to evaluate performances of various SBO planners for arm manipulation. However, not…

Recent studies have shown that episodic reinforcement learning (RL) is no harder than bandits when the total reward is bounded by $1$, and proved regret bounds that have a polylogarithmic dependence on the planning horizon $H$. However, it…

We study a class of adversarial bandit optimization problems in which the loss functions may be non-convex and non-smooth. In each round, the learner observes a loss that consists of an underlying linear component together with an…

We address the question of repeatedly learning linear classifiers against agents who are strategically trying to game the deployed classifiers, and we use the Stackelberg regret to measure the performance of our algorithms. First, we show…

Contextual bandits (CB) are online sequential decision-making problems under partial feedback that underpin many adaptive services. There is a growing demand to deploy CB agents directly on-device, under strict constraints on memory,…

Learning algorithms are essential for the applications of game theory in a networking environment. In dynamic and decentralized settings where the traffic, topology and channel states may vary over time and the communication between agents…

Contextual linear optimization (CLO) uses predictive contextual features to reduce uncertainty in random cost coefficients in the objective and thereby improve decision-making performance. A canonical example is the stochastic shortest path…

We study repeated two-player games where one of the players, the learner, employs a no-regret learning strategy, while the other, the optimizer, is a rational utility maximizer. We consider general Bayesian games, where the payoffs of both…

This paper studies a long-term resource allocation problem over multiple periods where each period requires a multi-stage decision-making process. We formulate the problem as an online allocation problem in an episodic finite-horizon…

Mobile edge computing seeks to provide resources to different delay-sensitive applications. However, allocating the limited edge resources to a number of applications is a challenging problem. To alleviate the resource scarcity problem, we…

We study the emergency of mutual cooperation in evolutionary prisoner's dilemma games when the players are located on a square lattice. The players can choose one of the three strategies: cooperation (C), defection (D) or "tit for tat" (T),…

A main problem of "Follow the Perturbed Leader" strategies for online decision problems is that regret bounds are typically proven against oblivious adversary. In partial observation cases, it was not clear how to obtain performance…

This paper explores multi-armed bandit (MAB) strategies in very short horizon scenarios, i.e., when the bandit strategy is only allowed very few interactions with the environment. This is an understudied setting in the MAB literature with…

Algorithms for hyperparameter optimization abound, all of which work well under different and often unverifiable assumptions. Motivated by the general challenge of sequentially choosing which algorithm to use, we study the more specific…

Offline model-based optimization (MBO) seeks to discover high-performing designs using only a fixed dataset of past evaluations. Most existing methods rely on learning a surrogate model via regression and implicitly assume that good…

We study off-policy learning (OPL) in contextual bandits, which plays a key role in a wide range of real-world applications such as recommendation systems and online advertising. Typical OPL in contextual bandits assumes an unconstrained…

This paper studies online shortest path routing over multi-hop networks. Link costs or delays are time-varying and modeled by independent and identically distributed random processes, whose parameters are initially unknown. The parameters,…

We consider online learning with feedback graphs, a sequential decision-making framework where the learner's feedback is determined by a directed graph over the action set. We present a computationally efficient algorithm for learning in…