Fully decentralized learning, where the global information, i.e., the actions of other agents, is inaccessible, is a fundamental challenge in cooperative multi-agent reinforcement learning. However, the convergence and optimality of most decentralized algorithms are not theoretically guaranteed, since the transition probabilities are non-stationary as all agents are updating policies simultaneously. To tackle this challenge, we propose best possible operator, a novel decentralized operator, and prove that the policies of agents will converge to the optimal joint policy if each agent independently updates its individual state-action value by the operator. Further, to make the update more efficient and practical, we simplify the operator and prove that the convergence and optimality still hold with the simplified one. By instantiating the simplified operator, the derived fully decentralized algorithm, best possible Q-learning (BQL), does not suffer from non-stationarity. Empirically, we show that BQL achieves remarkable improvement over baselines in a variety of cooperative multi-agent tasks.

With humans interacting with AI-based systems at an increasing rate, it is necessary to ensure the artificial systems are acting in a manner which reflects understanding of the human. In the case of humans and artificial AI agents operating in the same environment, we note the significance of comprehension and response to the actions or capabilities of a human from an agent's perspective, as well as the possibility to delegate decisions either to humans or to agents, depending on who is deemed more suitable at a certain point in time. Such capabilities will ensure an improved responsiveness and utility of the entire human-AI system. To that end, we investigate the use of cognitively inspired models of behavior to predict the behavior of both human and AI agents. The predicted behavior, and associated performance with respect to a certain goal, is used to delegate control between humans and AI agents through the use of an intermediary entity. As we demonstrate, this allows overcoming potential shortcomings of either humans or agents in the pursuit of a goal.

This study explores the problem of Multi-Agent Path Finding with continuous and stochastic travel times whose probability distribution is unknown. Our purpose is to manage a group of automated robots that provide package delivery services in a building where pedestrians and a wide variety of robots coexist, such as delivery services in office buildings, hospitals, and apartments. It is often the case with these real-world applications that the time required for the robots to traverse a corridor takes a continuous value and is randomly distributed, and the prior knowledge of the probability distribution of the travel time is limited. Multi-Agent Path Finding has been widely studied and applied to robot management systems; however, automating the robot operation in such environments remains difficult. We propose 1) online re-planning to update the action plan of robots while it is executed, and 2) parameter update to estimate the probability distribution of travel time using Bayesian inference as the delay is observed. We use a greedy heuristic to obtain solutions in a limited computation time. Through simulations, we empirically compare the performance of our method to those of existing methods in terms of the conflict probability and the actual travel time of robots. The simulation results indicate that the proposed method can find travel paths with at least 50% fewer conflicts and a shorter actual total travel time than existing methods. The proposed method requires a small number of trials to achieve the performance because the parameter update is prioritized on the important edges for path planning, thereby satisfying the requirements of quick implementation of robust planning of automated delivery services.

We introduce Nocturne, a new 2D driving simulator for investigating multi-agent coordination under partial observability. The focus of Nocturne is to enable research into inference and theory of mind in real-world multi-agent settings without the computational overhead of computer vision and feature extraction from images. Agents in this simulator only observe an obstructed view of the scene, mimicking human visual sensing constraints. Unlike existing benchmarks that are bottlenecked by rendering human-like observations directly using a camera input, Nocturne uses efficient intersection methods to compute a vectorized set of visible features in a C++ back-end, allowing the simulator to run at over 2000 steps-per-second. Using open-source trajectory and map data, we construct a simulator to load and replay arbitrary trajectories and scenes from real-world driving data. Using this environment, we benchmark reinforcement-learning and imitation-learning agents and demonstrate that the agents are quite far from human-level coordination ability and deviate significantly from the expert trajectories.

This paper presents a comprehensive review of ground agricultural robotic systems and applications with special focus on harvesting that span research and commercial products and results, as well as their enabling technologies. The majority of literature concerns the development of crop detection, field navigation via vision and their related challenges. Health monitoring, yield estimation, water status inspection, seed planting and weed removal are frequently encountered tasks. Regarding robotic harvesting, apples, strawberries, tomatoes and sweet peppers are mainly the crops considered in publications, research projects and commercial products. The reported harvesting agricultural robotic solutions, typically consist of a mobile platform, a single robotic arm/manipulator and various navigation/vision systems. This paper reviews reported development of specific functionalities and hardware, typically required by an operating agricultural robot harvester; they include (a) vision systems, (b) motion planning/navigation methodologies (for the robotic platform and/or arm), (c) Human-Robot-Interaction (HRI) strategies with 3D visualization, (d) system operation planning & grasping strategies and (e) robotic end-effector/gripper design. Clearly, automated agriculture and specifically autonomous harvesting via robotic systems is a research area that remains wide open, offering several challenges where new contributions can be made.

Multiagent reinforcement learning (MARL) has benefited significantly from population-based and game-theoretic training regimes. One approach, Policy-Space Response Oracles (PSRO), employs standard reinforcement learning to compute response policies via approximate best responses and combines them via meta-strategy selection. We augment PSRO by adding a novel search procedure with generative sampling of world states, and introduce two new meta-strategy solvers based on the Nash bargaining solution. We evaluate PSRO's ability to compute approximate Nash equilibrium, and its performance in two negotiation games: Colored Trails, and Deal or No Deal. We conduct behavioral studies where human participants negotiate with our agents ($N = 346$). We find that search with generative modeling finds stronger policies during both training time and test time, enables online Bayesian co-player prediction, and can produce agents that achieve comparable social welfare negotiating with humans as humans trading among themselves.

The integration of the physical capabilities of an industrial collaborative robot with a social virtual character may represent a viable solution to enhance the workers' perception of the system as an embodied social entity and increase social engagement and well-being at the workplace. An online study was setup using prerecorded video interactions in order to pilot potential advantages of different embodied configurations of the cobot-avatar system in terms of perceptions of Social Presence, cobot-avatar Unity and Social Role of the system, and explore the relation of these. In particular, two different configurations were explored and compared: the virtual character was displayed either on a tablet strapped onto the base of the cobot or on a large TV screen positioned at the back of the workcell. The results imply that participants showed no clear preference based on the constructs, and both configurations fulfill these basic criteria. In terms of the relations between the constructs, there were strong correlations between perception of Social Presence, Unity and Social Role (Collegiality). This gives a valuable insight into the role of these constructs in the perception of cobots as embodied social entities, and towards building cobots that support well-being at the workplace.

Machine learning (ML) tasks are one of the major workloads in today's edge computing networks. Existing edge-cloud schedulers allocate the requested amounts of resources to each task, falling short of best utilizing the limited edge resources for ML tasks. This paper proposes TapFinger, a distributed scheduler for edge clusters that minimizes the total completion time of ML tasks through co-optimizing task placement and fine-grained multi-resource allocation. To learn the tasks' uncertain resource sensitivity and enable distributed scheduling, we adopt multi-agent reinforcement learning (MARL) and propose several techniques to make it efficient, including a heterogeneous graph attention network as the MARL backbone, a tailored task selection phase in the actor network, and the integration of Bayes' theorem and masking schemes. We first implement a single-task scheduling version, which schedules at most one task each time. Then we generalize to the multi-task scheduling case, in which a sequence of tasks is scheduled simultaneously. Our design can mitigate the expanded decision space and yield fast convergence to optimal scheduling solutions. Extensive experiments using synthetic and test-bed ML task traces show that TapFinger can achieve up to 54.9% reduction in the average task completion time and improve resource efficiency as compared to state-of-the-art schedulers.

Social dilemmas can be considered situations where individual rationality leads to collective irrationality. The multi-agent reinforcement learning community has leveraged ideas from social science, such as social value orientations (SVO), to solve social dilemmas in complex cooperative tasks. In this paper, by first introducing the typical "division of labor or roles" mechanism in human society, we provide a promising solution for intertemporal social dilemmas (ISD) with SVOs. A novel learning framework, called Learning Roles with Emergent SVOs (RESVO), is proposed to transform the learning of roles into the social value orientation emergence, which is symmetrically solved by endowing agents with altruism to share rewards with other agents. An SVO-based role embedding space is then constructed by individual conditioning policies on roles with a novel rank regularizer and mutual information maximizer. Experiments show that RESVO achieves a stable division of labor and cooperation in ISDs with different complexity.

Computational models have become a powerful tool in the quantitative sciences to understand the behaviour of complex systems that evolve in time. However, they often contain a potentially large number of free parameters whose values cannot be obtained from theory but need to be inferred from data. This is especially the case for models in the social sciences, economics, or computational epidemiology. Yet many current parameter estimation methods are mathematically involved and computationally slow to run. In this paper we present a computationally simple and fast method to retrieve accurate probability densities for model parameters using neural differential equations. We present a pipeline comprising multi-agent models acting as forward solvers for systems of ordinary or stochastic differential equations, and a neural network to then extract parameters from the data generated by the model. The two combined create a powerful tool that can quickly estimate densities on model parameters, even for very large systems. We demonstrate the method on synthetic time series data of the SIR model of the spread of infection, and perform an in-depth analysis of the Harris-Wilson model of economic activity on a network, representing a non-convex problem. For the latter, we apply our method both to synthetic data and to data of economic activity across Greater London. We find that our method calibrates the model orders of magnitude more accurately than a previous study of the same dataset using classical techniques, while running between 195 and 390 times faster.