A natural solution concept for many multiagent settings is the Stackelberg equilibrium, under which a ``leader'' agent selects a strategy that maximizes its own payoff assuming the ``follower'' chooses their best response to this strategy. Recent work has presented asymmetric learning updates that can be shown to converge to the \textit{differential} Stackelberg equilibria of two-player differentiable games. These updates are ``coupled'' in the sense that the leader requires some information about the follower's payoff function. Such coupled learning rules cannot be applied to \textit{ad hoc} interactive learning settings, and can be computationally impractical even in centralized training settings where the follower's payoffs are known. In this work, we present an ``uncoupled'' learning process under which each player's learning update only depends on their observations of the other's behavior. We prove that this process converges to a local Stackelberg equilibrium under similar conditions as previous coupled methods. We conclude with a discussion of the potential applications of our approach to human--AI cooperation and multi-agent reinforcement learning.

The use of Agent-Based and Activity-Based modeling in transportation is rising due to the capability of addressing complex applications such as disruptive trends (e.g., remote working and automation) or the design and assessment of disaggregated management strategies. Still, the broad adoption of large-scale disaggregate models is not materializing due to the inherently high complexity and computational needs. Activity-based models focused on behavioral theory, for example, may involve hundreds of parameters that need to be calibrated to match the detailed socio-economical characteristics of the population for any case study. This paper tackles this issue by proposing a novel Bayesian Optimization approach incorporating a surrogate model in the form of an improved Random Forest, designed to automate the calibration process of the behavioral parameters. The proposed method is tested on a case study for the city of Tallinn, Estonia, where the model to be calibrated consists of 477 behavioral parameters, using the SimMobility MT software. Satisfactory performance is achieved in the major indicators defined for the calibration process: the error for the overall number of trips is equal to 4% and the average error in the OD matrix is 15.92 vehicles per day.

Recent advances in multi-agent reinforcement learning (MARL) allow agents to coordinate their behaviors in complex environments. However, common MARL algorithms still suffer from scalability and sparse reward issues. One promising approach to resolving them is automatic curriculum learning (ACL). ACL involves a student (curriculum learner) training on tasks of increasing difficulty controlled by a teacher (curriculum generator). Despite its success, ACL's applicability is limited by (1) the lack of a general student framework for dealing with the varying number of agents across tasks and the sparse reward problem, and (2) the non-stationarity of the teacher's task due to ever-changing student strategies. As a remedy for ACL, we introduce a novel automatic curriculum learning framework, Skilled Population Curriculum (SPC), which adapts curriculum learning to multi-agent coordination. Specifically, we endow the student with population-invariant communication and a hierarchical skill set, allowing it to learn cooperation and behavior skills from distinct tasks with varying numbers of agents. In addition, we model the teacher as a contextual bandit conditioned by student policies, enabling a team of agents to change its size while still retaining previously acquired skills. We also analyze the inherent non-stationarity of this multi-agent automatic curriculum teaching problem and provide a corresponding regret bound. Empirical results show that our method improves the performance, scalability and sample efficiency in several MARL environments.

Existing episodic reinforcement algorithms assume that the length of an episode is fixed across time and known a priori. In this paper, we consider a general framework of episodic reinforcement learning when the length of each episode is drawn from a distribution. We first establish that this problem is equivalent to online reinforcement learning with general discounting where the learner is trying to optimize the expected discounted sum of rewards over an infinite horizon, but where the discounting function is not necessarily geometric. We show that minimizing regret with this new general discounting is equivalent to minimizing regret with uncertain episode lengths. We then design a reinforcement learning algorithm that minimizes regret with general discounting but acts for the setting with uncertain episode lengths. We instantiate our general bound for different types of discounting, including geometric and polynomial discounting. We also show that we can obtain similar regret bounds even when the uncertainty over the episode lengths is unknown, by estimating the unknown distribution over time. Finally, we compare our learning algorithms with existing value-iteration based episodic RL algorithms in a grid-world environment.

A key component of cognitive radar is the ability to generalize, or achieve consistent performance across a range of sensing environments, since aspects of the physical scene may vary over time. This presents a challenge for learning-based waveform selection approaches, since transmission policies which are effective in one scene may be highly suboptimal in another. We address this problem by strategically biasing a learning algorithm by exploiting high-level structure across tracking instances, referred to as meta-learning. In this work, we develop an online meta-learning approach for waveform-agile tracking. This approach uses information gained from previous target tracks to speed up and enhance learning in new tracking instances. This results in sample-efficient learning across a class of finite state target channels by exploiting inherent similarity across tracking scenes, attributed to common physical elements such as target type or clutter statistics. We formulate the online waveform selection problem within the framework of Bayesian learning, and provide prior-dependent performance bounds for the meta-learning problem using Probability Approximately Correct (PAC)-Bayes theory. We present a computationally feasible meta-posterior sampling algorithm and study the performance in a simulation study consisting of diverse scenes. Finally, we examine the potential performance benefits and practical challenges associated with online meta-learning for waveform-agile tracking.

Dynamical networks are versatile models that can describe a variety of behaviours such as synchronisation and feedback. However, applying these models in real world contexts is difficult as prior information pertaining to the connectivity structure or local dynamics is often unknown and must be inferred from time series observations of network states. Additionally, the influence of coupling interactions between nodes further complicates the isolation of local node dynamics. Given the architectural similarities between dynamical networks and recurrent neural networks (RNN), we propose a network inference method based on the backpropagation through time (BPTT) algorithm commonly used to train recurrent neural networks. This method aims to simultaneously infer both the connectivity structure and local node dynamics purely from observation of node states. An approximation of local node dynamics is first constructed using a neural network. This is alternated with an adapted BPTT algorithm to regress corresponding network weights by minimising prediction errors of the dynamical network based on the previously constructed local models until convergence is achieved. This method was found to be succesful in identifying the connectivity structure for coupled networks of Lorenz, Chua and FitzHugh-Nagumo oscillators. Freerun prediction performance with the resulting local models and weights was found to be comparable to the true system with noisy initial conditions. The method is also extended to non-conventional network couplings such as asymmetric negative coupling.

Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to acquire new knowledge continually. For example, a robot needs to understand new instructions, and an opinion monitoring system should analyze emerging topics every day. Class-Incremental Learning (CIL) enables the learner to incorporate the knowledge of new classes incrementally and build a universal classifier among all seen classes. Correspondingly, when directly training the model with new class instances, a fatal problem occurs -- the model tends to catastrophically forget the characteristics of former ones, and its performance drastically degrades. There have been numerous efforts to tackle catastrophic forgetting in the machine learning community. In this paper, we survey comprehensively recent advances in deep class-incremental learning and summarize these methods from three aspects, i.e., data-centric, model-centric, and algorithm-centric. We also provide a rigorous and unified evaluation of 16 methods in benchmark image classification tasks to find out the characteristics of different algorithms empirically. Furthermore, we notice that the current comparison protocol ignores the influence of memory budget in model storage, which may result in unfair comparison and biased results. Hence, we advocate fair comparison by aligning the memory budget in evaluation, as well as several memory-agnostic performance measures. The source code to reproduce these evaluations is available at https://github.com/zhoudw-zdw/CIL_Survey/

Incorporating Artificial Intelligence (AI) into education has been met with enthusiasm and scepticism in almost equal measure. One of the main reasons for confidence towards AI in education is its potential to provide tailored learning experiences. By tracking a student's progress and understanding of the material, AI can adjust its teaching methods and resources to meet the student's specific needs, which can improve their knowledge. However, scepticism arises from the limitations of AI in understanding emotions and providing empathy, as well as the fear that it could replace human teachers and lead to job loss. AI has the potential to enhance the teaching-learning process greatly.

Welcome to World University and School Wiki which anyone can add to or edit. WUaS would like to offer online CLE credits with these great universities, anticipating accrediting WUaS Law Schools in 204 countries. California, the state in which WUaS is incorporated, has 12 online law schools (none of these are ABA approved, but anyone can sit the California Bar exam, regardless of such approval, as I understand it), at present, and WUaS would like to develop another online MIT OCW/Harvard-centric law school, and eventually accredit in all 204 countries in the world, in main languages in those countries, beginning with the 6 United Nations' languages. Online Law Schools Have Yet to Pass the Bar: Many argue that fully online programs aren't the path to a traditional legal career]. WUaS is planning for a "Admitted Students' Day" for the first, matriculating Bachelor's degree class, on or around Saturday, April 14th, 2014, and the second Saturday of April for other degrees in the future.

In this tutorial, you will learn to train a custom image classification network for OAK-D using the TensorFlow framework. Furthermore, this tutorial aims to develop an image classification model that can learn to classify one of the 15 vegetables (e.g., tomato, brinjal, and bottle gourd). If you are a regular PyImageSearch reader and have even basic knowledge of Deep Learning in Computer Vision, then this tutorial should be easy to understand. Furthermore, this tutorial acts as a foundation for the following tutorial, where we learn to deploy this trained image classification model on OAK-D. To learn how to train an image classification network for OAK-D, just keep reading. Before we start data loading, analysis, and training the classification network on the data, we must carefully pick the suitable classification architecture as it would finally be deployed on the OAK. Although OAK can process 4 trillion operations per second, it is still an edge device.