arXiv subjects

Shiva Navabi

Publications and source records attributed to Shiva Navabi.

5 recordsLinked to original sources

arXiv2020

A Generative Machine Learning Approach to Policy Optimization in Pursuit-Evasion Games

We consider a pursuit-evasion game [11] played between two agents, 'Blue' (the pursuer) and 'Red' (the evader), over $T$ time steps. Red aims to attack Blue's territory. Blue's objective is to intercept Red by time $T$ and thereby limit the success of Red's attack. Blue must plan its pursuit trajectory by choosing parameters that determine its course of movement (speed and angle in our setup) such that it intercepts Red by time $T$. We show that Blue's path-planning problem in pursuing Red, can be posed as a sequential decision making problem under uncertainty. Blue's unawareness of Red's action policy renders the analytic dynamic programming approach intractable for finding the optimal action policy for Blue. In this work, we are interested in exploring data-driven approaches to the policy optimization problem that Blue faces. We apply generative machine learning (ML) approaches to learn optimal action policies for Blue. This highlights the ability of generative ML model to learn the relevant implicit representations for the dynamics of simulated pursuit-evasion games. We demonstrate the effectiveness of our modeling approach via extensive statistical assessments. This work can be viewed as a preliminary step towards further adoption of generative modeling approaches for addressing policy optimization problems that arise in the context of multi-agent learning and planning [1].

cs.LG↗

arXiv2020

Optimal Dynamic Mechanism Design with Stochastic Supply and Flexible Consumers

We consider the problem of designing an expected-revenue maximizing mechanism for allocating multiple non-perishable goods of $k$ varieties to flexible consumers over $T$ time steps. In our model, a random number of goods of each variety may become available to the seller at each time and a random number of consumers may enter the market at each time. Each consumer is present in the market for one time step and wants to consume one good of one of its desired varieties. Each consumer is associated with a flexibility level that indicates the varieties of the goods it is equally interested in. A consumer's flexibility level and the utility it gets from consuming a good of its desired varieties are its private information. We characterize the allocation rule for a Bayesian incentive compatible, individually rational and expected revenue maximizing mechanism in terms of the solution to a dynamic program. The corresponding payment function is also specified in terms of the optimal allocation function. We leverage the structure of the consumers' flexibility model to simplify the dynamic program and provide an alternative description of the optimal mechanism in terms of thresholds computed by the dynamic program.

cs.GT↗

arXiv2018

Predicting Wireless Channel Features using Neural Networks

We investigate the viability of using machine-learning techniques for estimating user-channel features at a large-array base station (BS). In the scenario we consider, user-pilot broadcasts are observed and processed by the BS to extract angle-of-arrival (AoA) specific information about propagation-channel features, such as received signal strength and relative path delay. The problem of interest involves using this information to predict the angle-of-departure (AoD) of the dominant propagation paths in the user channels, i.e., channel features not directly observable at the BS. To accomplish this task, the data collected in the same propagation environment are used to train neural networks. Our studies rely on ray-tracing channel data that have been calibrated against measurements from Shinjuku Square, a famous hotspot in Tokyo, Japan. We demonstrate that the observed features at the BS side are correlated with the angular features at the user side. We train neural networks that exploit different combinations of measured features at the BS to infer the unknown parameters at the users. The evaluation based on standard statistical performance metrics suggests that such data-driven methods have the potential to predict unobserved channel features from observed ones.

eess.SP↗

arXiv2018

Optimal Auction Design for Flexible Consumers

We study the problem of designing revenue-maximizing auctions for allocating multiple goods to flexible consumers. In our model, each consumer is interested in a subset of goods known as its flexibility set and wants to consume one good from this set. A consumer's flexibility set and its utility from consuming a good from its flexibility set are its private information. We focus on the case of nested flexibility sets --- each consumer's flexibility set can be one of $k$ nested sets. We provide several examples where such nested flexibility sets may arise. We characterize the allocation rule for an incentive compatible, individually rational and revenue-maximizing auction as the solution to an integer program. The corresponding payment rule is described by an integral equation. We then leverage the nestedness of flexibility sets to simplify the optimal auction and provide a complete characterization of allocations and payments in terms of simple thresholds.

cs.GT↗

arXiv2017

Optimal Mechanism Design with Flexible Consumers and Costly Supply

The problem of designing a profit-maximizing, Bayesian incentive compatible and individually rational mechanism with flexible consumers and costly heterogeneous supply is considered. In our setup, each consumer is associated with a flexibility set that describes the subset of goods the consumer is equally interested in. Each consumer wants to consume one good from its flexibility set. The flexibility set of a consumer and the utility it gets from consuming a good from its flexibility set are its private information. We adopt the flexibility model of [1] and focus on the case of nested flexibility sets -- each consumer's flexibility set can be one of k nested sets. Examples of settings with this inherent nested structure are provided. On the supply side, we assume that the seller has an initial stock of free supply but it can purchase more goods for each of the nested sets at fixed exogenous prices. We characterize the allocation and purchase rules for a profit-maximizing, Bayesian incentive compatible and individually rational mechanism as the solution to an integer program. The optimal payment function is pinned down by the optimal allocation rule in the form of an integral equation. We show that the nestedness of flexibility sets can be exploited to obtain a simple description of the optimal allocations, purchases and payments in terms of thresholds that can be computed through a straightforward iterative procedure.

cs.GT↗