The problem of achieving common understanding between agents that use different vocabularies has been mainly addressed by techniques that assume the existence of shared external elements, such as a meta-language or a physical environment. In this article, we consider agents that use different vocabularies and only share knowledge of how to perform a task, given by the specification of an interaction protocol. We present a framework that lets agents learn a vocabulary alignment from the experience of interacting. Unlike previous work in this direction, we use open protocols that constrain possible actions instead of defining procedures, making our approach more general. We present two techniques that can be used either to learn an alignment from scratch or to repair an existent one, and we evaluate their performance experimentally.

When it comes to finding a match/partner in the real world, it is usually an independent and autonomous task performed by people/entities. For a person, a match can be several things such as a romantic partner, business partner, school, roommate, etc. Our purpose in this paper is to train autonomous agents to find suitable matches for themselves using reinforcement learning. We consider the decentralized two-sided stable matching problem, where an agent is allowed to have at most one partner at a time from the opposite set. Each agent receives some utility for being in a match with a member of the opposite set. We formulate the problem spatially as a grid world environment and having autonomous agents acting independently makes our environment very uncertain and dynamic. We run experiments with various instances of both complete and incomplete weighted preference lists for agents. Agents learn their policies separately, using separate training modules. Our goal is to train agents to find partners such that the outcome is a stable matching if one exists and also a matching with set-equality, meaning the outcome is approximately equally likable by agents from both the sets.

Artificial intelligence (AI) has evolved into a new era, and its rapid development will profoundly affect the everyday life of citizens worldwide. Countries around the world are establishing governmental strategies and initiatives to guide the development of AI. The Chinese government is using the development of AI as a major strategy to enhance national competitiveness and protect national security. In January 2016, the Chinese State Council released the 13th Five-year Plan on National Science and Technology Innovation, explicitly putting forward the guidance, general requirements, strategic mission and reform measures for Chinese science and technology innovation. Over the next five years, smart manufacturing will be one of the major missions of the "Science and Technology Innovation 2030 Project" and there will be a focus on the development of AI technology.

In this paper, the fuzzy multi-objective reliability redundancy allocation problem (FMORRAP) is proposed, which maximizes the system reliability while simultaneously minimizing the system cost under the type 2 fuzzy uncertainty. In the proposed formulation, the higher order uncertainties (such as parametric, manufacturing, environmental, and designers uncertainty) associated with the system are modeled with interval type 2 fuzzy sets (IT2 FS). The footprint of uncertainty of the interval type 2 membership functions (IT2 MFs) accommodates these uncertainties by capturing the multiple opinions from several system experts. We consider IT2 MFs to represent the subsystem reliability and cost, which are to be further aggregated using extension principle to evaluate the total system reliability and cost according to their configurations, i.e., series parallel and parallel series. We proposed a particle swarm optimization (PSO) based novel solution approach to solve the FMORRAP. To demonstrate the applicability of two formulations, namely, series parallel FMORRAP and parallel series FMORRAP, we performed experimental simulations on various numerical data sets. The decision makers/system experts assign different importance to the objectives (system reliability and cost), and these preferences are represented by sets of weights. The optimal results are obtained from our solution approach, and the Pareto optimal front is established using these different weight sets. The genetic algorithm (GA) was implemented to compare the results obtained from our proposed solution approach. A statistical analysis was conducted between PSO and GA, and it was found that the PSO based Pareto solution outperforms the GA.

The goal of this thesis is to design a learning model predictive controller (LMPC) that allows multiple agents to race competitively on a predefined race track in real-time. This thesis addresses two major shortcomings in the already existing single-agent formulation. Previously, the agent determines a locally optimal trajectory but does not explore the state space, which may be necessary for overtaking maneuvers. Additionally, obstacle avoidance for LMPC has been achieved in the past by using a non-convex terminal set, which increases the complexity for determining a solution to the optimization problem. The proposed algorithm for multi-agent racing explores the state space by executing the LMPC for multiple different initializations, which yields a richer terminal safe set. Furthermore, a new method for selecting states in the terminal set is developed, which keeps the convexity for the terminal safe set and allows for taking suboptimal states.

This paper considers the decentralized optimization problem, which has applications in large scale machine learning, sensor networks, and control theory. We propose a novel algorithm that can achieve near optimal communication complexity, matching the known lower bound up to a logarithmic factor of the condition number of the problem. Our theoretical results give affirmative answers to the open problem on whether there exists an algorithm that can achieve a communication complexity (nearly) matching the lower bound depending on the global condition number instead of the local one. Moreover, the proposed algorithm achieves the optimal computation complexity matching the lower bound up to universal constants. Furthermore, to achieve a linear convergence rate, our algorithm \emph{doesn't} require the individual functions to be (strongly) convex. Our method relies on a novel combination of known techniques including Nesterov's accelerated gradient descent, multi-consensus and gradient-tracking. The analysis is new, and may be applied to other related problems. Empirical studies demonstrate the effectiveness of our method for machine learning applications.

Salesforce today announced the AI Economist, a research environment designed to elucidate how economic design might be improved with techniques from the field of AI and machine learning. The goal is to help economists, governments, and others design tax policies that optimize not only productivity and conservation, but that promote widespread, whole-country social equality. Studies have shown that income inequality gaps can negatively impact economic growth, economic opportunity, and even health. For example, over-taxation can discourage people from working, leading to lower productivity. But it's difficult to experiment with tax policies in the real world, at least in part because economic theory relies on stylized assumptions that are tough to validate, like people's sensitivity to taxes. The AI Economist, then, learns the best tax policies from simulations in which citizens and a government adapt and learn.

Walk-based models have shown their unique advantages in knowledge graph (KG) reasoning by achieving state-of-the-art performance while allowing for explicit visualization of the decision sequence. However, the sparse reward signals offered by the KG during a traversal are often insufficient to guide a sophisticated reinforcement learning (RL) model. An alternate approach to KG reasoning is using traditional symbolic methods (e.g., rule induction), which achieve high precision without learning but are hard to generalize due to the limitation of symbolic representation. In this paper, we propose to fuse these two paradigms to get the best of both worlds. Our method leverages high-quality rules generated by symbolic-based methods to provide reward supervision for walk-based agents. Due to the structure of symbolic rules with their entity variables, we can separate our walk-based agent into two sub-agents thus allowing for additional efficiency. Experiments on public datasets demonstrate that walk-based models can benefit from rule guidance significantly.

Smart modular freight containers -- as propagated in the Physical Internet paradigm -- are equipped with sensors, data storage capability and intelligence that enable them to route themselves from origin to destination without manual intervention or central governance. In this self-organizing setting, containers can autonomously place bids on transport services in a spot market setting. However, for individual containers it may be difficult to learn good bidding policies due to limited observations. By sharing information and costs between one another, smart containers can jointly learn bidding policies, even though simultaneously competing for the same transport capacity. We replicate this behavior by learning stochastic bidding policies in a semi-cooperative multi agent setting. To this end, we develop a reinforcement learning algorithm based on the policy gradient framework. Numerical experiments show that sharing solely bids and acceptance decisions leads to stable bidding policies. Additional system information only marginally improves performance; individual job properties suffice to place appropriate bids. Furthermore, we find that carriers may have incentives not to share information with the smart containers. The experiments give rise to several directions for follow-up research, in particular the interaction between smart containers and transport services in self-organizing logistics.

Following a navigation instruction such as'Walk down the stairs and stop at the brown sofa' requires embodied AI agents to ground scene elements referenced via language (e.g.'stairs') to visual content in the environment (pixels corresponding to'stairs'). We ask the following question - can we leverage abundant'disembodied' web-scraped vision-and-language corpora (e.g. Conceptual Captions [24]) to learn visual groundings (what do'stairs' look like?) that improve performance on a relatively data-starved embodied perception task (Visionand-Language Navigation)? Specifically, we develop VLN-BERT, a visiolinguistic transformer-based model for scoring the compatibility between an instruction ('...stop at the brown sofa') and a sequence of panoramic RGB images captured by the agent. We demonstrate that pretraining VLN-BERT on image-text pairs from the web before fine-tuning on embodied path-instruction data significantly improves performance on VLN - outperforming the prior state-of-the-art in the fully-observed setting by 4 absolute percentage points on success rate. Ablations of our pretraining curriculum show each stage to be impactful - with their combination resulting in further positive synergistic effects.