We propose a new Markov Decision Process (MDP) model for ad auctions to capture the user response to the quality of ads, with the objective of maximizing the long-term discounted revenue. By incorporating user response, our model takes into consideration all three parties involved in the auction (advertiser, auctioneer, and user). The state of the user is modeled as a user-specific click-through rate (CTR) with the CTR changing in the next round according to the set of ads shown to the user in the current round. We characterize the optimal mechanism for this MDP as a Myerson's auction with a notion of modified virtual value, which relies on the value distribution of the advertiser, the current user state, and the future impact of showing the ad to the user. Moreover, we propose a simple mechanism built upon second price auctions with personalized reserve prices and show it can achieve a constant-factor approximation to the optimal long term discounted revenue.

The symbolic AI community is increasingly trying to embrace machine learning in neuro-symbolic architectures, yet is still struggling due to cultural barriers. To break the barrier, this rather opinionated personal memo attempts to explain and rectify the conventions in Statistics, Machine Learning, and Deep Learning from the viewpoint of outsiders. It provides a step-by-step protocol for designing a machine learning system that satisfies a minimum theoretical guarantee necessary for being taken seriously by the symbolic AI community, i.e., it discusses "in what condition we can stop worrying and accept statistical machine learning." Unlike most textbooks which are written for students trying to specialize in Stat/ML/DL and willing to accept jargons, this memo is written for experienced symbolic researchers that hear a lot of buzz but are still uncertain and skeptical. Information on Stat/ML/DL is currently too scattered or too noisy to invest in. This memo prioritizes compactness, citations to old papers (many in early 20th century), and concepts that resonate well with symbolic paradigms in order to offer time savings. It prioritizes general mathematical modeling and does not discuss any specific function approximator, such as neural networks (NNs), SVMs, decision trees, etc. Finally, it is open to corrections. Consider this memo as something similar to a blog post taking the form of a paper on Arxiv.

We consider the problem of testing the identity of a reversible Markov chain against a reference from a single trajectory of observations. Employing the recently introduced notion of a lumping-congruent Markov embedding, we show that, at least in a mildly restricted setting, testing identity to a reversible chain reduces to testing to a symmetric chain over a larger state space and recover state-of-the-art sample complexity for the problem.

Knowledge tracing (KT) serves as a primary part of intelligent education systems. Most current KTs either rely on expert judgments or only exploit a single network structure, which affects the full expression of learning features. To adequately mine features of students' learning process, Deep Knowledge Tracing Based on Spatial and Temporal Deep Representation Learning for Learning Performance Prediction (DKT-STDRL) is proposed in this paper. DKT-STDRL extracts spatial features from students' learning history sequence, and then further extracts temporal features to extract deeper hidden information. Specifically, firstly, the DKT-STDRL model uses CNN to extract the spatial feature information of students' exercise sequences. Then, the spatial features are connected with the original students' exercise features as joint learning features. Then, the joint features are input into the BiLSTM part. Finally, the BiLSTM part extracts the temporal features from the joint learning features to obtain the prediction information of whether the students answer correctly at the next time step. Experiments on the public education datasets ASSISTment2009, ASSISTment2015, Synthetic-5, ASSISTchall, and Statics2011 prove that DKT-STDRL can achieve better prediction effects than DKT and CKT.

Cross-silo federated learning (FL) is a typical FL that enables organizations(e.g., financial or medical entities) to train global models on isolated data. Reasonable incentive is key to encouraging organizations to contribute data. However, existing works on incentivizing cross-silo FL lack consideration of the environmental dynamics (e.g., precision of the trained global model and data owned by uncertain clients during the training processes). Moreover, most of them assume that organizations share private information, which is unrealistic. To overcome these limitations, we propose a novel adaptive mechanism for cross-silo FL, towards incentivizing organizations to contribute data to maximize their long-term payoffs in a real dynamic training environment. The mechanism is based on multi-agent reinforcement learning, which learns near-optimal data contribution strategy from the history of potential games without organizations' private information. Experiments demonstrate that our mechanism achieves adaptive incentive and effectively improves the long-term payoffs for organizations.

This work presents a novel, inference-based approach to the distributed and cooperative flocking control of aerial robot swarms. The proposed method stems from the Unmanned Aerial Vehicle (UAV) dynamics by limiting the latent set to the robots' feasible action space, thus preventing any unattainable control inputs from being produced and leading to smooth flocking behavior. By modeling the inter-agent relationships using a pairwise energy function, we show that interacting robot swarms constitute a Markov Random Field. Our algorithm builds on the Mean-Field Approximation and incorporates the collective behavioral rules: cohesion, separation, and velocity alignment. We follow a distributed control scheme and show that our method can control a swarm of UAVs to a formation and velocity consensus with real-time collision avoidance. We validate the proposed method with physical UAVs and high-fidelity simulation experiments.

The recent advancements in wireless technology enable connected autonomous vehicles (CAVs) to gather data via vehicle-to-vehicle (V2V) communication, such as processed LIDAR and camera data from other vehicles. In this work, we design an integrated information sharing and safe multi-agent reinforcement learning (MARL) framework for CAVs, to take advantage of the extra information when making decisions to improve traffic efficiency and safety. We first use weight pruned convolutional neural networks (CNN) to process the raw image and point cloud LIDAR data locally at each autonomous vehicle, and share CNN-output data with neighboring CAVs. We then design a safe actor-critic algorithm that utilizes both a vehicle's local observation and the information received via V2V communication to explore an efficient behavior planning policy with safety guarantees. Using the CARLA simulator for experiments, we show that our approach improves the CAV system's efficiency in terms of average velocity and comfort under different CAV ratios and different traffic densities. We also show that our approach avoids the execution of unsafe actions and always maintains a safe distance from other vehicles. We construct an obstacle-at-corner scenario to show that the shared vision can help CAVs to observe obstacles earlier and take action to avoid traffic jams.

Reinforcement learning (RL) describes the interaction between a learning agent and an unknown environment, where the agent aims to maximize the cumulative reward through trial and error Sutton and Barto [2018]. It has achieved great success in many real applications, such as games [Mnih et al., 2013; Silver et al., 2016], robotics [Kober et al., 2013; Lillicrap et al., 2015], autonomous driving [Kiran et al., 2021] and recommendation systems [Afsar et al., 2022; Lin et al., 2021]. The interaction in RL is commonly portrayed by Markov decision processes (MDP). Most of the works study the stochastic setting, where the reward is sampled from a fixed distribution [Azar et al., 2017; Jin et al., 2018; Simchowitz and Jamieson, 2019; Yang et al., 2021]. RL in real applications is in general more challenging than the stochastic setting, as the environment could be nonstationary and the reward function could be adaptive towards the agent's policy. For example, a scheduling algorithm will be deployed to self-interested parties, and recommendation algorithms will face strategic users. To design robust algorithms that work under non-stationary environments, a line of works focuses on the adversarial setting, where the reward function could be arbitrarily chosen by an adversary [Yu et al., 2009; Rosenberg and Mansour, 2019; Jin et al., 2020a; Chen et al., 2021; Luo et al., 2021a].

Active Simultaneous Localization and Mapping (SLAM) is the problem of planning and controlling the motion of a robot to build the most accurate and complete model of the surrounding environment. Since the first foundational work in active perception appeared, more than three decades ago, this field has received increasing attention across different scientific communities. This has brought about many different approaches and formulations, and makes a review of the current trends necessary and extremely valuable for both new and experienced researchers. In this work, we survey the state-of-the-art in active SLAM and take an in-depth look at the open challenges that still require attention to meet the needs of modern applications. After providing a historical perspective, we present a unified problem formulation and review the well-established modular solution scheme, which decouples the problem into three stages that identify, select, and execute potential navigation actions. We then analyze alternative approaches, including belief-space planning and deep reinforcement learning techniques, and review related work on multi-robot coordination. The manuscript concludes with a discussion of new research directions, addressing reproducible research, active spatial perception, and practical applications, among other topics.

Knowledge and skills can transfer from human teachers to human students. However, such direct transfer is often not scalable for physical tasks, as they require one-to-one interaction, and human teachers are not available in sufficient numbers. Machine learning enables robots to become experts and play the role of teachers to help in this situation. In this work, we formalize cooperative robot teaching as a Markov game, consisting of four key elements: the target task, the student model, the teacher model, and the interactive teaching-learning process. Under a moderate assumption, the Markov game reduces to a partially observable Markov decision process, with an efficient approximate solution. We illustrate our approach on two cooperative tasks, one in a simulated video game and one with a real robot.