arXiv subjects

Fei Fang

Publications and source records attributed to Fei Fang.

At least 127 records · Page 7Linked to original sources

arXiv2019

Signal Instructed Coordination in Cooperative Multi-agent Reinforcement Learning

In many real-world problems, a team of agents need to collaborate to maximize the common reward. Although existing works formulate this problem into a centralized learning with decentralized execution framework, which avoids the non-stationary problem in training, their decentralized execution paradigm limits the agents' capability to coordinate. Inspired by the concept of correlated equilibrium, we propose to introduce a coordination signal to address this limitation, and theoretically show that following mild conditions, decentralized agents with the coordination signal can coordinate their individual policies as manipulated by a centralized controller. The idea of introducing coordination signal is to encapsulate coordinated strategies into the signals, and use the signals to instruct the collaboration in decentralized execution. To encourage agents to learn to exploit the coordination signal, we propose Signal Instructed Coordination (SIC), a novel coordination module that can be integrated with most existing MARL frameworks. SIC casts a common signal sampled from a pre-defined distribution to all agents, and introduces an information-theoretic regularization to facilitate the consistency between the observed signal and agents' policies. Our experiments show that SIC consistently improves performance over well-recognized MARL models in both matrix games and a predator-prey game with high-dimensional strategy space.

cs.MA↗

arXiv2019

Draining the Water Hole: Mitigating Social Engineering Attacks with CyberTWEAK

Cyber adversaries have increasingly leveraged social engineering attacks to breach large organizations and threaten the well-being of today's online users. One clever technique, the "watering hole" attack, compromises a legitimate website to execute drive-by download attacks by redirecting users to another malicious domain. We introduce a game-theoretic model that captures the salient aspects for an organization protecting itself from a watering hole attack by altering the environment information in web traffic so as to deceive the attackers. Our main contributions are (1) a novel Social Engineering Deception (SED) game model that features a continuous action set for the attacker, (2) an in-depth analysis of the SED model to identify computationally feasible real-world cases, and (3) the CyberTWEAK algorithm which solves for the optimal protection policy. To illustrate the potential use of our framework, we built a browser extension based on our algorithms which is now publicly available online. The CyberTWEAK extension will be vital to the continued development and deployment of countermeasures for social engineering.

cs.CR↗

arXiv2019

Correlation in Extensive-Form Games: Saddle-Point Formulation and Benchmarks

While Nash equilibrium in extensive-form games is well understood, very little is known about the properties of extensive-form correlated equilibrium (EFCE), both from a behavioral and from a computational point of view. In this setting, the strategic behavior of players is complemented by an external device that privately recommends moves to agents as the game progresses; players are free to deviate at any time, but will then not receive future recommendations. Our contributions are threefold. First, we show that an EFCE can be formulated as the solution to a bilinear saddle-point problem. To showcase how this novel formulation can inspire new algorithms to compute EFCEs, we propose a simple subgradient descent method which exploits this formulation and structural properties of EFCEs. Our method has better scalability than the prior approach based on linear programming. Second, we propose two benchmark games, which we hope will serve as the basis for future evaluation of EFCE solvers. These games were chosen so as to cover two natural application domains for EFCE: conflict resolution via a mediator, and bargaining and negotiation. Third, we document the qualitative behavior of EFCE in our proposed games. We show that the social-welfare-maximizing equilibria in these games are highly nontrivial and exhibit surprisingly subtle sequential behavior that so far has not received attention in the literature.

cs.GT↗

arXiv2019

Efficient Regret Minimization Algorithm for Extensive-Form Correlated Equilibrium

Self-play methods based on regret minimization have become the state of the art for computing Nash equilibria in large two-players zero-sum extensive-form games. These methods fundamentally rely on the hierarchical structure of the players' sequential strategy spaces to construct a regret minimizer that recursively minimizes regret at each decision point in the game tree. In this paper, we introduce the first efficient regret minimization algorithm for computing extensive-form correlated equilibria in large two-player general-sum games with no chance moves. Designing such an algorithm is significantly more challenging than designing one for the Nash equilibrium counterpart, as the constraints that define the space of correlation plans lack the hierarchical structure and might even form cycles. We show that some of the constraints are redundant and can be excluded from consideration, and present an efficient algorithm that generates the space of extensive-form correlation plans incrementally from the remaining constraints. This structural decomposition is achieved via a special convexity-preserving operation that we coin scaled extension. We show that a regret minimizer can be designed for a scaled extension of any two convex sets, and that from the decomposition we then obtain a global regret minimizer. Our algorithm produces feasible iterates. Experiments show that it significantly outperforms prior approaches and for larger problems it is the only viable option.

cs.GT↗

arXiv2019

A Robot's Expressive Language Affects Human Strategy and Perceptions in a Competitive Game

As robots are increasingly endowed with social and communicative capabilities, they will interact with humans in more settings, both collaborative and competitive. We explore human-robot relationships in the context of a competitive Stackelberg Security Game. We vary humanoid robot expressive language (in the form of "encouraging" or "discouraging" verbal commentary) and measure the impact on participants' rationality, strategy prioritization, mood, and perceptions of the robot. We learn that a robot opponent that makes discouraging comments causes a human to play a game less rationally and to perceive the robot more negatively. We also contribute a simple open source Natural Language Processing framework for generating expressive sentences, which was used to generate the speech of our autonomous social robot.

cs.HC↗

arXiv2019

Dynamic Trip-Vehicle Dispatch with Scheduled and On-Demand Requests

Transportation service providers that dispatch drivers and vehicles to riders start to support both on-demand ride requests posted in real time and rides scheduled in advance, leading to new challenges which, to the best of our knowledge, have not been addressed by existing works. To fill the gap, we design novel trip-vehicle dispatch algorithms to handle both types of requests while taking into account an estimated request distribution of on-demand requests. At the core of the algorithms is the newly proposed Constrained Spatio-Temporal value function (CST-function), which is polynomial-time computable and represents the expected value a vehicle could gain with the constraint that it needs to arrive at a specific location at a given time. Built upon CST-function, we design a randomized best-fit algorithm for scheduled requests and an online planning algorithm for on-demand requests given the scheduled requests as constraints. We evaluate the algorithms through extensive experiments on a real-world dataset of an online ride-hailing platform.

cs.AI↗

arXiv2019

Large Scale Learning of Agent Rationality in Two-Player Zero-Sum Games

With the recent advances in solving large, zero-sum extensive form games, there is a growing interest in the inverse problem of inferring underlying game parameters given only access to agent actions. Although a recent work provides a powerful differentiable end-to-end learning frameworks which embed a game solver within a deep-learning framework, allowing unknown game parameters to be learned via backpropagation, this framework faces significant limitations when applied to boundedly rational human agents and large scale problems, leading to poor practicality. In this paper, we address these limitations and propose a framework that is applicable for more practical settings. First, seeking to learn the rationality of human agents in complex two-player zero-sum games, we draw upon well-known ideas in decision theory to obtain a concise and interpretable agent behavior model, and derive solvers and gradients for end-to-end learning. Second, to scale up to large, real-world scenarios, we propose an efficient first-order primal-dual method which exploits the structure of extensive-form games, yielding significantly faster computation for both game solving and gradient computation. When tested on randomly generated games, we report speedups of orders of magnitude over previous approaches. We also demonstrate the effectiveness of our model on both real-world one-player settings and synthetic data.

cs.LG↗

arXiv2019

Artificial Intelligence for Social Good

The Computing Community Consortium (CCC), along with the White House Office of Science and Technology Policy (OSTP), and the Association for the Advancement of Artificial Intelligence (AAAI), co-sponsored a public workshop on Artificial Intelligence for Social Good on June 7th, 2016 in Washington, DC. This was one of five workshops that OSTP co-sponsored and held around the country to spur public dialogue on artificial intelligence, machine learning, and to identify challenges and opportunities related to AI. In the AI for Social Good workshop, the successful deployments and the potential use of AI in various topics that are essential for social good were discussed, including but not limited to urban computing, health, environmental sustainability, and public welfare. This report highlights each of these as well as a number of crosscutting issues.

cs.CY↗

arXiv2018

On the Inducibility of Stackelberg Equilibrium for Security Games

Strong Stackelberg equilibrium (SSE) is the standard solution concept of Stackelberg security games. As opposed to the weak Stackelberg equilibrium (WSE), the SSE assumes that the follower breaks ties in favor of the leader and this is widely acknowledged and justified by the assertion that the defender can often induce the attacker to choose a preferred action by making an infinitesimal adjustment to her strategy. Unfortunately, in security games with resource assignment constraints, the assertion might not be valid; it is possible that the defender cannot induce the desired outcome. As a result, many results claimed in the literature may be overly optimistic. To remedy, we first formally define the utility guarantee of a defender strategy and provide examples to show that the utility of SSE can be higher than its utility guarantee. Second, inspired by the analysis of leader's payoff by Von Stengel and Zamir (2004), we provide the solution concept called the inducible Stackelberg equilibrium (ISE), which owns the highest utility guarantee and always exists. Third, we show the conditions when ISE coincides with SSE and the fact that in general case, SSE can be extremely worse with respect to utility guarantee. Moreover, introducing the ISE does not invalidate existing algorithmic results as the problem of computing an ISE polynomially reduces to that of computing an SSE. We also provide an algorithmic implementation for computing ISE, with which our experiments unveil the empirical advantage of the ISE over the SSE.

cs.GT↗

arXiv2018

Deep Reinforcement Learning for Green Security Games with Real-Time Information

Green Security Games (GSGs) have been proposed and applied to optimize patrols conducted by law enforcement agencies in green security domains such as combating poaching, illegal logging and overfishing. However, real-time information such as footprints and agents' subsequent actions upon receiving the information, e.g., rangers following the footprints to chase the poacher, have been neglected in previous work. To fill the gap, we first propose a new game model GSG-I which augments GSGs with sequential movement and the vital element of real-time information. Second, we design a novel deep reinforcement learning-based algorithm, DeDOL, to compute a patrolling strategy that adapts to the real-time information against a best-responding attacker. DeDOL is built upon the double oracle framework and the policy-space response oracle, solving a restricted game and iteratively adding best response strategies to it through training deep Q-networks. Exploring the game structure, DeDOL uses domain-specific heuristic strategies as initial strategies and constructs several local modes for efficient and parallelized training. To our knowledge, this is the first attempt to use Deep Q-Learning for security games.

cs.MA↗

arXiv2018

Tractable Graph Matching via Soft Seeding

The graph matching problem aims to discover a latent correspondence between the vertex sets of two observed graphs. This problem has proven to be quite challenging, with few satisfying methods that are computationally tractable and widely applicable. The FAQ algorithm has proven to have good performance on benchmark problems and works with a indefinite relaxation of the problem. Due to the indefinite relaxation, FAQ is not guaranteed to find the global maximum. However, if prior information is known about the true correspondence, this can be leveraged to initialize the algorithm near the truth. We show that given certain properties of this initial matrix, with high probability the FAQ algorithm will converge in two steps to the truth under a flexible model for pairs of random graphs. Importantly, this result implies that there will be no local optima near the global optima, providing a method to assess performance.

stat.CO↗

arXiv2018

The energy identity of Sacks-Uhlenbeck operator and infinitely many solutions for Brezis-Nirenberg problem

Let $Ω$ be a bounded smooth domain in $\mathbb{R}^N$ with $N\geq 3$, $1<α$, $2^{\ast}=\frac{2N}{N-2}$ and $\{u_α\}\subset H_{0}^{1,2α}(Ω)$ be a critical point of the functional \begin{equation*} I_{α,λ}(u)=\frac{1}{2α}\int\limits_Ω [(1+|\nabla u|^2)^α-1 ]dx-\fracλ{2}\int\limits_Ωu^2dx-\frac{1}{2^{\ast}}\int\limits_Ω|u|^{2^{\ast}}dx. \end{equation*} In this paper, we obtain the limit behaviour of $u_α$ ( $α\rightarrow 1$), energy identity, Pohozaev identity, some integral estimates, etc. And using these results, we prove infinitely many solutions for the following Brezis-Nirenberg problem for $N\geq 7$: \begin{equation*} \left\{ \begin{aligned} &-Δu=|u|^{2^{\ast}-2}u+λu\ \ \ \mbox{in}\ Ω,\\ &u=0,\ \ \mbox{on}\ \partialΩ. \end{aligned} \right. \end{equation*}

math.AP↗

arXiv2018

What game are we playing? End-to-end learning in normal and extensive form games

Although recent work in AI has made great progress in solving large, zero-sum, extensive-form games, the underlying assumption in most past work is that the parameters of the game itself are known to the agents. This paper deals with the relatively under-explored but equally important "inverse" setting, where the parameters of the underlying game are not known to all agents, but must be learned through observations. We propose a differentiable, end-to-end learning framework for addressing this task. In particular, we consider a regularized version of the game, equivalent to a particular form of quantal response equilibrium, and develop 1) a primal-dual Newton method for finding such equilibrium points in both normal and extensive form games; and 2) a backpropagation method that lets us analytically compute gradients of all relevant game parameters through the solution itself. This ultimately lets us learn the game by training in an end-to-end fashion, effectively by integrating a "differentiable game solver" into the loop of larger deep network architectures. We demonstrate the effectiveness of the learning method in several settings including poker and security game tasks.

cs.LG↗

arXiv2018

The cone Moser-Trudinger inequalities and their applications

In this article, we firstly study the cone Moser-Trudinger inequalities and their best exponents $α_2$ on both bounded and unbounded domains $\mathbb{R}^2_{+}$. Then, using the cone Moser-Trudinger inequalities, we study the existence of weak solutions to the nonlinear equation \begin{equation*} \left\{\begin{array}{ll} -Δ_{\mathbb{B}} u=f(x, u), &\mbox{in}\ x\in \mbox{int} (\mathbb{B}), \\ u= 0, &\mbox{on}\ \partial\mathbb{B}, \end{array} \right. \end{equation*} where $Δ_{\mathbb{B}}$ is Fuchsian type Laplace operator investigated with totally characteristic degeneracy on the boundary $x_1 =0$, and the nonlinearity $f$ has the subcritical exponential growth or the critical exponential growth.

math.AP↗

arXiv2018

The Impact of Humanoid Affect Expression on Human Behavior in a Game-Theoretic Setting

With the rapid development of robot and other intelligent and autonomous agents, how a human could be influenced by a robot's expressed mood when making decisions becomes a crucial question in human-robot interaction. In this pilot study, we investigate (1) in what way a robot can express a certain mood to influence a human's decision making behavioral model; (2) how and to what extent the human will be influenced in a game theoretic setting. More specifically, we create an NLP model to generate sentences that adhere to a specific affective expression profile. We use these sentences for a humanoid robot as it plays a Stackelberg security game against a human. We investigate the behavioral model of the human player.

cs.HC↗

arXiv2018

Designing the Game to Play: Optimizing Payoff Structure in Security Games

Effective game-theoretic modeling of defender-attacker behavior is becoming increasingly important. In many domains, the defender functions not only as a player but also the designer of the game's payoff structure. We study Stackelberg Security Games where the defender, in addition to allocating defensive resources to protect targets from the attacker, can strategically manipulate the attacker's payoff under budget constraints in weighted L^p-norm form regarding the amount of change. Focusing on problems with weighted L^1-norm form constraint, we present (i) a mixed integer linear program-based algorithm with approximation guarantee; (ii) a branch-and-bound based algorithm with improved efficiency achieved by effective pruning; (iii) a polynomial time approximation scheme for a special but practical class of problems. In addition, we show that problems under budget constraints in L^0-norm form and weighted L^\infty-norm form can be solved in polynomial time. We provide an extensive experimental evaluation of our proposed algorithms.

cs.GT↗

arXiv2018

Exploiting Data and Human Knowledge for Predicting Wildlife Poaching

Poaching continues to be a significant threat to the conservation of wildlife and the associated ecosystem. Estimating and predicting where the poachers have committed or would commit crimes is essential to more effective allocation of patrolling resources. The real-world data in this domain is often sparse, noisy and incomplete, consisting of a small number of positive data (poaching signs), a large number of negative data with label uncertainty, and an even larger number of unlabeled data. Fortunately, domain experts such as rangers can provide complementary information about poaching activity patterns. However, this kind of human knowledge has rarely been used in previous approaches. In this paper, we contribute new solutions to the predictive analysis of poaching patterns by exploiting both very limited data and human knowledge. We propose an approach to elicit quantitative information from domain experts through a questionnaire built upon a clustering-based division of the conservation area. In addition, we propose algorithms that exploit qualitative and quantitative information provided by the domain experts to augment the dataset and improve learning. In collaboration with World Wild Fund for Nature, we show that incorporating human knowledge leads to better predictions in a conservation area in Northeastern China where the charismatic species is Siberian Tiger. The results show the importance of exploiting human knowledge when learning from limited data.

cs.CY↗

arXiv2017

Video Labeling for Automatic Video Surveillance in Security Domains

Beyond traditional security methods, unmanned aerial vehicles (UAVs) have become an important surveillance tool used in security domains to collect the required annotated data. However, collecting annotated data from videos taken by UAVs efficiently, and using these data to build datasets that can be used for learning payoffs or adversary behaviors in game-theoretic approaches and security applications, is an under-explored research question. This paper presents VIOLA, a novel labeling application that includes (i) a workload distribution framework to efficiently gather human labels from videos in a secured manner; (ii) a software interface with features designed for labeling videos taken by UAVs in the domain of wildlife security. We also present the evolution of VIOLA and analyze how the changes made in the development process relate to the efficiency of labeling, including when seemingly obvious improvements did not lead to increased efficiency. VIOLA enables collecting massive amounts of data with detailed information from challenging security videos such as those collected aboard UAVs for wildlife security. VIOLA will lead to the development of new approaches that integrate deep learning for real-time detection and response.

cs.CY↗