This paper investigates the network load balancing problem in data centers (DCs) where multiple load balancers (LBs) are deployed, using the multi-agent reinforcement learning (MARL) framework. The challenges of this problem consist of the heterogeneous processing architecture and dynamic environments, as well as limited and partial observability of each LB agent in distributed networking systems, which can largely degrade the performance of in-production load balancing algorithms in real-world setups. Centralised-training-decentralised-execution (CTDE) RL scheme has been proposed to improve MARL performance, yet it incurs -- especially in distributed networking systems, which prefer distributed and plug-and-play design scheme -- additional communication and management overhead among agents. We formulate the multi-agent load balancing problem as a Markov potential game, with a carefully and properly designed workload distribution fairness as the potential function. A fully distributed MARL algorithm is proposed to approximate the Nash equilibrium of the game. Experimental evaluations involve both an event-driven simulator and real-world system, where the proposed MARL load balancing algorithm shows close-to-optimal performance in simulations, and superior results over in-production LBs in the real-world system.

The uses of robots are changing from static environments in factories to encompass novel concepts such as Human-Robot Collaboration in unstructured settings. Pre-programming all the functionalities for robots becomes impractical, and hence, robots need to learn how to react to new events autonomously, just like humans. However, humans, unlike machines, are naturally skilled in responding to unexpected circumstances based on either experiences or observations. Hence, embedding such anthropoid behaviours into robots entails the development of neuro-cognitive models that emulate motor skills under a robot learning paradigm. Effective encoding of these skills is bound to the proper choice of tools and techniques. This paper studies different motion and behaviour learning methods ranging from Movement Primitives (MP) to Experience Abstraction (EA), applied to different robotic tasks. These methods are scrutinized and then experimentally benchmarked by reconstructing a standard pick-n-place task. Apart from providing a standard guideline for the selection of strategies and algorithms, this paper aims to draw a perspectives on their possible extensions and improvements

The ability to reuse previous policies is an important aspect of human intelligence. To achieve efficient policy reuse, a Deep Reinforcement Learning (DRL) agent needs to decide when to reuse and which source policies to reuse. Previous methods solve this problem by introducing extra components to the underlying algorithm, such as hierarchical high-level policies over source policies, or estimations of source policies' value functions on the target task. However, training these components induces either optimization non-stationarity or heavy sampling cost, significantly impairing the effectiveness of transfer. To tackle this problem, we propose a novel policy reuse algorithm called Critic-gUided Policy reuse (CUP), which avoids training any extra components and efficiently reuses source policies. CUP utilizes the critic, a common component in actor-critic methods, to evaluate and choose source policies. At each state, CUP chooses the source policy that has the largest one-step improvement over the current target policy, and forms a guidance policy. The guidance policy is theoretically guaranteed to be a monotonic improvement over the current target policy. Then the target policy is regularized to imitate the guidance policy to perform efficient policy search. Empirical results demonstrate that CUP achieves efficient transfer and significantly outperforms baseline algorithms.

The 35th edition of the IEA/AIE2022 (International Conference on Industrial, Engineering, and Other Applications of Applied Intelligent Systems) was hosted in hybrid mode from July 19th to July 22nd, 2022, in Kitakyushu, Japan. IEA/AIE is an annual conference dedicated to advances related to the theory and applications of artificial intelligence that started in 1988 and has been hosted in over twenty countries. IEA/AIE 2022 was organized in cooperation with the American Association of Artificial Intelligence (AAAI), the ACM Special Interest Group on Artificial Intelligence (SIGAI) and has received the support of Springer, the International Society of Applied Intelligence (ISAI), Kitakyushu city, Universiti Teknologi Malaysia, i-SOMET Inc., and several other international Organizations. The conference had a main track and five special sessions for emerging topics in applied intelligence, named Spatiotemporal Big Data Analytics (SBDA 2022), Intelligent Systems and e-Applications (ISeA 2022), Collective Intelligence in Social Media (CISM 2022), Multi-Agent Systems and Metaheuristics for Complex Problems (MASMCP 2022), and Intelligent Knowledge Engineering in Decision Making Systems (IKEDS 2022). All the submissions were peer-reviewed by at least three reviewers following a double-blind process.

We propose a practical integration of logical state abstraction with AIXI, a Bayesian optimality notion for reinforcement learning agents, to significantly expand the model class that AIXI agents can be approximated over to complex history-dependent and structured environments. The state representation and reasoning framework is based on higher-order logic, which can be used to define and enumerate complex features on non-Markovian and structured environments. We address the problem of selecting the right subset of features to form state abstractions by adapting the $\Phi$-MDP optimisation criterion from state abstraction theory. Exact Bayesian model learning is then achieved using a suitable generalisation of Context Tree Weighting over abstract state sequences. The resultant architecture can be integrated with different planning algorithms. Experimental results on controlling epidemics on large-scale contact networks validates the agent's performance.

A popular algorithm configuration tuning paradigm is dynamic algorithm configuration (DAC), in which an agent learns dynamic configuration policies across instances by reinforcement learning (RL). However, in many complex algorithms, there may exist different types of configuration hyperparameters, and such heterogeneity may bring difficulties for classic DAC which uses a single-agent RL policy. In this paper, we aim to address this issue and propose multi-agent DAC (MA-DAC), with one agent working for one type of configuration hyperparameter. MA-DAC formulates the dynamic configuration of a complex algorithm with multiple types of hyperparameters as a contextual multi-agent Markov decision process and solves it by a cooperative multi-agent RL (MARL) algorithm. To instantiate, we apply MA-DAC to a well-known optimization algorithm for multi-objective optimization problems. Experimental results show the effectiveness of MA-DAC in not only achieving superior performance compared with other configuration tuning approaches based on heuristic rules, multi-armed bandits, and single-agent RL, but also being capable of generalizing to different problem classes. Furthermore, we release the environments in this paper as a benchmark for testing MARL algorithms, with the hope of facilitating the application of MARL.

We introduce a new framework that performs decision-making in reinforcement learning (RL) as an iterative reasoning process. We model agent behavior as the steady-state distribution of a parameterized reasoning Markov chain (RMC), optimized with a new tractable estimate of the policy gradient. We perform action selection by simulating the RMC for enough reasoning steps to approach its steady-state distribution. We show our framework has several useful properties that are inherently missing from traditional RL. For instance, it allows agent behavior to approximate any continuous distribution over actions by parameterizing the RMC with a simple Gaussian transition function. Moreover, the number of reasoning steps to reach convergence can scale adaptively with the difficulty of each action selection decision and can be accelerated by re-using past solutions. Our resulting algorithm achieves state-of-the-art performance in popular Mujoco and DeepMind Control benchmarks, both for proprioceptive and pixel-based tasks.

The advent of deep learning (DL) gave rise to significant breakthroughs in Reinforcement Learning (RL) research. Deep Reinforcement Learning (DRL) algorithms have reached super-human level skills when applied to vision-based control problems as such in Atari 2600 games where environment states were extracted from pixel information. Unfortunately, these environments are far from being applicable to highly dynamic and complex real-world tasks as in autonomous control of a fighter aircraft since these environments only involve 2D representation of a visual world. Here, we present a semi-realistic flight simulation environment Harfang3D Dog-Fight Sandbox for fighter aircrafts. It is aimed to be a flexible toolbox for the investigation of main challenges in aviation studies using Reinforcement Learning. The program provides easy access to flight dynamics model, environment states, and aerodynamics of the plane enabling user to customize any specific task in order to build intelligent decision making (control) systems via RL. The software also allows deployment of bot aircrafts and development of multi-agent tasks. This way, multiple groups of aircrafts can be configured to be competitive or cooperative agents to perform complicated tasks including Dog Fight. During the experiments, we carried out training for two different scenarios: navigating to a designated location and within visual range (WVR) combat, shortly Dog Fight. Using Deep Reinforcement Learning techniques for both scenarios, we were able to train competent agents that exhibit human-like behaviours. Based on this results, it is confirmed that Harfang3D Dog-Fight Sandbox can be utilized as a 3D realistic RL research platform.

We consider the non-metric data placement problem and develop distributed algorithms for computing or approximating its optimal integral solution. We first show that the non-metric data placement problem is inapproximable up to a logarithmic factor. We then provide a game-theoretic decomposition of the objective function and show that natural Glauber dynamics in which players update their resources with probability proportional to the utility they receive from caching those resources will converge to an optimal global solution for a sufficiently large noise parameter. In particular, we establish the polynomial mixing time of the Glauber dynamics for a certain range of noise parameters. Finally, we provide another auction-based distributed algorithm, which allows us to approximate the optimal global solution with a performance guarantee that depends on the ratio of the revenue vs. social welfare obtained from the underlying auction. Our results provide the first distributed computation algorithms for the non-metric data placement problem.

Agent-based modelling (ABM) is a facet of wider Multi-Agent Systems (MAS) research that explores the collective behaviour of individual `agents', and the implications that their behaviour and interactions have for wider systemic behaviour. The method has been shown to hold considerable value in exploring and understanding human societies, but is still largely confined to use in academia. This is particularly evident in the field of Urban Analytics; one that is characterised by the use of new forms of data in combination with computational approaches to gain insight into urban processes. In Urban Analytics, ABM is gaining popularity as a valuable method for understanding the low-level interactions that ultimately drive cities, but as yet is rarely used by stakeholders (planners, governments, etc.) to address real policy problems. This paper presents the state-of-the-art in the application of ABM at the interface of MAS and Urban Analytics by a group of ABM researchers who are affiliated with the Urban Analytics programme of the Alan Turing Institute in London (UK). It addresses issues around modelling behaviour, the use of new forms of data, the calibration of models under high uncertainty, real-time modelling, the use of AI techniques, large-scale models, and the implications for modelling policy. The discussion also contextualises current research in wider debates around Data Science, Artificial Intelligence, and MAS more broadly.