We introduce the first temporal-difference learning algorithm that is stable with linear function approximation and off-policy training, for any finite Markov decision process, target policy, and exciting behavior policy, and whose complexity scales linearly in the number of parameters. We consider an i.i.d.\ policy-evaluation setting in which the data need not come from on-policy experience. The gradient temporal-difference (GTD) algorithm estimates the expected update vector of the TD(0) algorithm and performs stochastic gradient descent on its L_2 norm. Our analysis proves that its expected update is in the direction of the gradient, assuring convergence under the usual stochastic approximation conditions to the same least-squares solution as found by the LSTD, but without its quadratic computational complexity. GTD is online and incremental, and does not involve multiplying by products of likelihood ratios as in importance-sampling methods.

We introduce the first temporal-difference learning algorithms that converge with smooth value function approximators, such as neural networks. Conventional temporal-difference (TD) methods, such as TD( \lambda), Q-learning and Sarsa have been used successfully with function approximation in many applications. However, it is well known that off-policy sampling, as well as nonlinear function approximation, can cause these algorithms to become unstable (i.e., the parameters of the approximator may diverge). Sutton et al (2009a,b) solved the problem of off-policy learning with linear TD algorithms by introducing a new objective function, related to the Bellman-error, and algorithms that perform stochastic gradient-descent on this function. In this paper, we generalize their work to nonlinear function approximation.

Markov Games (MG) is an important model for Multi-Agent Reinforcement Learning (MARL). It was long believed that the "curse of multi-agents" (i.e., the algorithmic performance drops exponentially with the number of agents) is unavoidable until several recent works (Daskalakis et al., 2023; Cui et al., 2023; Wang et al., 2023. While these works did resolve the curse of multi-agents, when the state spaces are prohibitively large and (linear) function approximations are deployed, they either had a slower convergence rate of $O(T^{-1/4})$ or brought a polynomial dependency on the number of actions $A_{\max}$ -- which is avoidable in single-agent cases even when the loss functions can arbitrarily vary with time (Dai et al., 2023). This paper first refines the `AVLPR` framework by Wang et al. (2023), with an insight of *data-dependent* (i.e., stochastic) pessimistic estimation of the sub-optimality gap, allowing a broader choice of plug-in algorithms. When specialized to MGs with independent linear function approximations, we propose novel *action-dependent bonuses* to cover occasionally extreme estimation errors. With the help of state-of-the-art techniques from the single-agent RL literature, we give the first algorithm that tackles the curse of multi-agents, attains the optimal $O(T^{-1/2})$ convergence rate, and avoids $\text{poly}(A_{\max})$ dependency simultaneously.

In the past few decades, the rapid development of information and internet technologies has spawned massive amounts of data and information. The information explosion drives many enterprises or individuals to seek to rent cloud computing infrastructure to put their applications in the cloud. However, the agreements reached between cloud computing providers and clients are often not efficient. Many factors affect the efficiency, such as the idleness of the providers' cloud computing infrastructure, and the additional cost to the clients. One possible solution is to introduce a comprehensive, bargaining game (a type of negotiation), and schedule resources according to the negotiation results. We propose an agent-based auto-negotiation system for resource scheduling based on fuzzy logic. The proposed method can complete a one-to-one auto-negotiation process and generate optimal offers for the provider and client. We compare the impact of different member functions, fuzzy rule sets, and negotiation scenario cases on the offers to optimize the system. It can be concluded that our proposed method can utilize resources more efficiently and is interpretable, highly flexible, and customizable. We successfully train machine learning models to replace the fuzzy negotiation system to improve processing speed. The article also highlights possible future improvements to the proposed system and machine learning models. All the codes and data are available in the open-source repository.

Classic Delphi and Fuzzy Delphi methods are used to test content validity of a data collection tools such as questionnaires. Fuzzy Delphi takes the opinion issued by judges from a linguistic perspective reducing ambiguity in opinions by using fuzzy numbers. We propose an extension named 2-Tuple Fuzzy Linguistic Delphi method to deal with scenarios in which judges show different expertise degrees by using fuzzy multigranular semantics of the linguistic terms and to obtain intermediate and final results expressed by 2-tuple linguistic values. The key idea of our proposal is to validate the full questionnaire by means of the evaluation of its parts, defining the validity of each item as a Decision Making problem. Taking the opinion of experts, we measure the degree of consensus, the degree of consistency, and the linguistic score of each item, in order to detect those items that affect, positively or negatively, the quality of the instrument. Considering the real need to evaluate a b-learning educational experience with a consensual questionnaire, we present a Decision Making model for questionnaire validation that solve it. Additionally, we contribute to this consensus reaching problem by developing an online tool under GPL v3 license. The software visualizes the collective valuations for each iteration and assists to determine which parts of the questionnaire should be modified to reach a consensual solution.

Accurately estimating risk in real-time is essential for ensuring the safety and efficiency of many applications involving autonomous robot systems. This paper presents a novel, generalizable algorithm for the real-time estimation of risks created by external disturbances on multirotors. Unlike conventional approaches, our method requires no additional sensors, accurate drone models, or large datasets. It employs motor command data in a fuzzy logic system, overcoming barriers to real-world implementation. Inherently adaptable, it utilizes fundamental drone characteristics, making it applicable to diverse drone models. The efficiency of the algorithm has been confirmed through comprehensive real-world testing on various platforms. It proficiently discerned between high and low-risk scenarios resulting from diverse wind disturbances and varying thrust-to-weight ratios. The algorithm surpassed the widely-recognized ArduCopter wind estimation algorithm in performance and demonstrated its capability to promptly detect brief gusts.

This comprehensive review article delves into the intricate realm of fault-tolerant control (FTC) schemes tailored for robotic manipulators. Our exploration spans the historical evolution of FTC, tracing its development over time, and meticulously examines the recent breakthroughs fueled by the synergistic integration of cutting-edge technologies such as artificial intelligence (AI), machine learning (ML), and digital twin technologies (DTT). The article places a particular emphasis on the transformative influence these contemporary trends exert on the landscape of robotic manipulator control and fault tolerance. By delving into the historical context, our aim is to provide a comprehensive understanding of the evolution of FTC schemes. This journey encompasses the transition from model-based and signal-based schemes to the role of sensors, setting the stage for an exploration of the present-day paradigm shift enabled by AI, ML, and DTT. The narrative unfolds as we dissect the intricate interplay between these advanced technologies and their applications in enhancing fault tolerance within the domain of robotic manipulators. Our review critically evaluates the impact of these advancements, shedding light on the novel methodologies, techniques, and applications that have emerged in recent times. The overarching goal of this article is to present a comprehensive perspective on the current state of fault diagnosis and fault-tolerant control within the context of robotic manipulators, positioning our exploration within the broader framework of AI, ML, and DTT advancements. Through a meticulous examination of both historical foundations and contemporary innovations, this review significantly contributes to the existing body of knowledge, offering valuable insights for researchers, practitioners, and enthusiasts navigating the dynamic landscape of robotic manipulator control.

In the last 5 years, the availability of large audio datasets in African countries has opened unlimited opportunities to build machine intelligence (MI) technologies that are closer to the people and speak, learn, understand, and do businesses in local languages, including for those who cannot read and write. Unfortunately, these audio datasets are not fully exploited by current MI tools, leaving several Africans out of MI business opportunities. Additionally, many state-of-the-art MI models are not culture-aware, and the ethics of their adoption indexes are questionable. The lack thereof is a major drawback in many applications in Africa. This paper summarizes recent developments in machine intelligence in Africa from a multi-layer multiscale and culture-aware ethics perspective, showcasing MI use cases in 54 African countries through 400 articles on MI research, industry, government actions, as well as uses in art, music, the informal economy, and small businesses in Africa. The survey also opens discussions on the reliability of MI rankings and indexes in the African continent as well as algorithmic definitions of unclear terms used in MI.

This paper describes an architecture for predicting the price of cryptocurrencies for the next seven days using the Adaptive Network Based Fuzzy Inference System (ANFIS). Historical data of cryptocurrencies and indexes that are considered are Bitcoin (BTC), Ethereum (ETH), Bitcoin Dominance (BTC.D), and Ethereum Dominance (ETH.D) in The architectural performance designed in this paper has been compared with different inputs and neural network models in terms of statistical evaluation criteria. Finally, the proposed method can predict the price of digital currencies in a short time. NTRODUCTION Digital currency is a form of electronic money that operates on the internet and possesses most of the attributes of conventional money, except for its physical absence. A subset of digital currency is cryptocurrency, which is encrypted by specific algorithms. These cryptocurrencies often utilize blockchain technology to record transactions [1]. The main distinction between cryptocurrencies and other digital currencies is the level of security of the former.

In recent years, there has been a lot of research work activity focused on carrying out asymptotic and non-asymptotic convergence analyses for two-timescale actor critic algorithms where the actor updates are performed on a timescale that is slower than that of the critic. In a recent work, the critic-actor algorithm has been presented for the infinite horizon discounted cost setting in the look-up table case where the timescales of the actor and the critic are reversed and asymptotic convergence analysis has been presented. In our work, we present the first critic-actor algorithm with function approximation and in the long-run average reward setting and present the first finite-time (non-asymptotic) analysis of such a scheme. We obtain optimal learning rates and prove that our algorithm achieves a sample complexity of $\mathcal{\tilde{O}}(\epsilon^{-2.08})$ for the mean squared error of the critic to be upper bounded by $\epsilon$ which is better than the one obtained for actor-critic in a similar setting. We also show the results of numerical experiments on three benchmark settings and observe that the critic-actor algorithm competes well with the actor-critic algorithm.