Cooperative multi-agent reinforcement learning (MARL) has achieved significant results, most notably by leveraging the representation learning abilities of deep neural networks. However, large centralized approaches quickly become infeasible as the number of agents scale, and fully decentralized approaches can miss important opportunities for information sharing and coordination. Furthermore, not all agents are equal - in some cases, individual agents may not even have the ability to send communication to other agents or explicitly model other agents. This paper considers the case where there is a single, powerful, central agent that can observe the entire observation space, and there are multiple, low powered, local agents that can only receive local observations and cannot communicate with each other. The job of the central agent is to learn what message to send to different local agents, based on the global observations, not by centrally solving the entire problem and sending action commands, but by determining what additional information an individual agent should receive so that it can make a better decision. After explaining our MARL algorithm, hammer, and where it would be most applicable, we implement it in the cooperative navigation and multi-agent walker domains. Empirical results show that 1) learned communication does indeed improve system performance, 2) results generalize to multiple numbers of agents, and 3) results generalize to different reward structures.

Recent years saw a plethora of work on explaining complex intelligent agents. One example is the development of several algorithms that generate saliency maps which show how much each pixel attributed to the agents' decision. However, most evaluations of such saliency maps focus on image classification tasks. As far as we know, there is no work which thoroughly compares different saliency maps for Deep Reinforcement Learning agents. This paper compares four perturbation-based approaches to create saliency maps for Deep Reinforcement Learning agents trained on four different Atari 2600 games. All four approaches work by perturbing parts of the input and measuring how much this affects the agent's output. The approaches are compared using three computational metrics: dependence on the learned parameters of the agent (sanity checks), faithfulness to the agent's reasoning (input degradation), and run-time.

Modeling mixed-traffic motion and interactions is crucial to assess safety, efficiency, and feasibility of future urban areas. The lack of traffic regulations, diverse transport modes, and the dynamic nature of mixed-traffic zones like shared spaces make realistic modeling of such environments challenging. This paper focuses on the generalizability of the motion model, i.e., its ability to generate realistic behavior in different environmental settings, an aspect which is lacking in existing works. Specifically, our first contribution is a novel and systematic process of formulating general motion models and application of this process is to extend our Game-Theoretic Social Force Model (GSFM) towards a general model for generating a large variety of motion behaviors of pedestrians and cars from different shared spaces. Our second contribution is to consider different motion patterns of pedestrians by calibrating motion-related features of individual pedestrian and clustering them into groups. We analyze two clustering approaches. The calibration and evaluation of our model are performed on three different shared space data sets. The results indicate that our model can realistically simulate a wide range of motion behaviors and interaction scenarios, and that adding different motion patterns of pedestrians into our model improves its performance.

Training a multi-agent reinforcement learning (MARL) algorithm is more challenging than training a single-agent reinforcement learning algorithm, because the result of a multi-agent task strongly depends on the complex interactions among agents and their interactions with a stochastic and dynamic environment. We propose an algorithm that boosts MARL training using the biased action information of other agents based on a friend-or-foe concept. For a cooperative and competitive environment, there are generally two groups of agents: cooperative-agents and competitive-agents. In the proposed algorithm, each agent updates its value function using its own action and the biased action information of other agents in the two groups. The biased joint action of cooperative agents is computed as the sum of their actual joint action and the imaginary cooperative joint action, by assuming all the cooperative agents jointly maximize the target agent's value function. The biased joint action of competitive agents can be computed similarly. Each agent then updates its own value function using the biased action information, resulting in a biased value function and corresponding biased policy. Subsequently, the biased policy of each agent is inevitably subjected to recommend an action to cooperate and compete with other agents, thereby introducing more active interactions among agents and enhancing the MARL policy learning. We empirically demonstrate that our algorithm outperforms existing algorithms in various mixed cooperative-competitive environments. Furthermore, the introduced biases gradually decrease as the training proceeds and the correction based on the imaginary assumption vanishes.

The advent of artificial intelligence (AI) and machine learning (ML) bring human-AI interaction to the forefront of HCI research. This paper argues that games are an ideal domain for studying and experimenting with how humans interact with AI. Through a systematic survey of neural network games (n = 38), we identified the dominant interaction metaphors and AI interaction patterns in these games. In addition, we applied existing human-AI interaction guidelines to further shed light on player-AI interaction in the context of AI-infused systems. Our core finding is that AI as play can expand current notions of human-AI interaction, which are predominantly productivity-based. In particular, our work suggests that game and UX designers should consider flow to structure the learning curve of human-AI interaction, incorporate discovery-based learning to play around with the AI and observe the consequences, and offer users an invitation to play to explore new forms of human-AI interaction.

This paper describes a method combining Bayesian optimization (BO) and a lamped-capacitance thermal circuit network model that is effective for speeding up the thermal design optimization of an electronic circuit board layout with transient heating chips. As electronic devices have become smaller and more complex, the importance of thermal design optimization to ensure heat dissipation performance has increased. However, such thermal design optimization is difficult because it is necessary to consider various trade-offs associated with packaging and transient temperature changes of heat-generating components. This study aims to improve the performance of thermal design optimization by artificial intelligence. BO using a Gaussian process was combined with the lamped-capacitance thermal circuit network model, and its performance was verified by case studies. As a result, BO successfully found the ideal circuit board layout as well as particle swarm optimization (PSO) and genetic algorithm (GA) could. The CPU time for BO was 1/5 and 1/4 of that for PSO and GA, respectively. In addition, BO found a non-intuitive optimal solution in approximately 7 minutes from 10 million layout patterns. It was estimated that this was 1/1000 of the CPU time required for analyzing all layout patterns.

Simulation has the potential to massively scale evaluation of self-driving systems enabling rapid development as well as safe deployment. To close the gap between simulation and the real world, we need to simulate realistic multi-agent behaviors. Existing simulation environments rely on heuristic-based models that directly encode traffic rules, which cannot capture irregular maneuvers (e.g., nudging, U-turns) and complex interactions (e.g., yielding, merging). In contrast, we leverage real-world data to learn directly from human demonstration and thus capture a more diverse set of actor behaviors. To this end, we propose TrafficSim, a multi-agent behavior model for realistic traffic simulation. In particular, we leverage an implicit latent variable model to parameterize a joint actor policy that generates socially-consistent plans for all actors in the scene jointly. To learn a robust policy amenable for long horizon simulation, we unroll the policy in training and optimize through the fully differentiable simulation across time. Our learning objective incorporates both human demonstrations as well as common sense. We show TrafficSim generates significantly more realistic and diverse traffic scenarios as compared to a diverse set of baselines. Notably, we can exploit trajectories generated by TrafficSim as effective data augmentation for training better motion planner.

Kubernetes (k8s) has the potential to merge the distributed edge and the cloud but lacks a scheduling framework specifically for edge-cloud systems. Besides, the hierarchical distribution of heterogeneous resources and the complex dependencies among requests and resources make the modeling and scheduling of k8s-oriented edge-cloud systems particularly sophisticated. In this paper, we introduce KaiS, a learning-based scheduling framework for such edge-cloud systems to improve the long-term throughput rate of request processing. First, we design a coordinated multi-agent actor-critic algorithm to cater to decentralized request dispatch and dynamic dispatch spaces within the edge cluster. Second, for diverse system scales and structures, we use graph neural networks to embed system state information, and combine the embedding results with multiple policy networks to reduce the orchestration dimensionality by stepwise scheduling. Finally, we adopt a two-time-scale scheduling mechanism to harmonize request dispatch and service orchestration, and present the implementation design of deploying the above algorithms compatible with native k8s components. Experiments using real workload traces show that KaiS can successfully learn appropriate scheduling policies, irrespective of request arrival patterns and system scales. Moreover, KaiS can enhance the average system throughput rate by 14.3% while reducing scheduling cost by 34.7% compared to baselines.

We study the multi-agent safe control problem where agents should avoid collisions to static obstacles and collisions with each other while reaching their goals. Our core idea is to learn the multi-agent control policy jointly with learning the control barrier functions as safety certificates. We propose a novel joint-learning framework that can be implemented in a decentralized fashion, with generalization guarantees for certain function classes. Such a decentralized framework can adapt to an arbitrarily large number of agents. Building upon this framework, we further improve the scalability by incorporating neural network architectures that are invariant to the quantity and permutation of neighboring agents. In addition, we propose a new spontaneous policy refinement method to further enforce the certificate condition during testing. We provide extensive experiments to demonstrate that our method significantly outperforms other leading multi-agent control approaches in terms of maintaining safety and completing original tasks. Our approach also shows exceptional generalization capability in that the control policy can be trained with 8 agents in one scenario, while being used on other scenarios with up to 1024 agents in complex multi-agent environments and dynamics.

There are many practitioners that create software to buy and sell financial assets in an autonomous way. There are some digital platforms that allow the development, test and deployment of trading agents (or robots) in simulated or real markets. Some of these work focus on very short horizons of investment, while others deal with longer periods. The spectrum of used AI techniques in finance field is wide. There are many cases, where the developers are successful in creating robots with great performance in historical price series (so called backtesting). Furthermore, some platforms make available thousands of robots that [allegedly] are able to be profitable in real markets. These strategies may be created with some simple idea or using complex machine learning schemes. Nevertheless, when they are used in real markets or with data not used in their training or evaluation frequently they present very poor performance. In this paper, we propose a method for testing Foreign Exchange (FX) trading strategies that can provide realistic expectations about strategy's performance. This method addresses many pitfalls that can fool even experience practitioners and researchers. We present the results of applying such method in several famous autonomous strategies in many different financial assets. Analyzing these results, we can realize that it is very hard to build a reliable strategy and many published strategies are far from being reliable vehicles of investment. These facts can be maliciously used by those who try to sell such robots, by advertising such great (and non repetitive) results, while hiding the bad but meaningful results. The proposed method can be used to select among potential robots, establishes minimal periods and requirements for the test executions. In this way, the method helps to tell if you really have a great trading strategy or you are just fooling yourself.