In this paper we deal with a practical problem that arises in military situations. The problem is to plan a path for one (or more) agents to reach a target without being detected by enemy sensors. Agents are not passive, rather they can (within limits) initiate actions which aid evasion, namely knockout (completely disable sensors) and confusion (reduce sensor detection probabilities). Agent actions are path dependent and time limited. Here by path dependent we mean that an agent needs to be sufficiently close to a sensor to knock it out. By time limited we mean that a limit is imposed on how long a sensor is knocked out or confused before it reverts back to its original operating state. The approach adopted breaks the continuous space in which agents move into a discrete space. This enables the problem to be represented (formulated) mathematically as a zero-one integer program with linear constraints. The advantage of representing the problem in this manner is that powerful commercial software optimisation packages exist to solve the problem to proven global optimality. Computational results are presented for a number of randomly generated test problems.

Consider a standard non-cooperative negotiation game (Deming et al., 1944; Successful negotiators must learn how to balance Nash, 1950; 1951) as shown in Figure 1 where two agents - optimizing for self-interest and cooperation. Yet Alice and Bob - are trying to agree on an allocation of shared current artificial negotiation agents often heavily resources. Both have high utility associated with the hats depend on the quality of the static datasets they and balls, though Alice also cares about books. Effectively were trained on, limiting their capacity to fashion employing negotiation is crucial, and is the only way to an adaptive response balancing self-interest and reach an equitable outcome - dividing the hats and balls cooperation. For this reason, we find that these evenly, while giving Alice the book. Even where negotiating agents can achieve either high utility or cooperation, agents have incentives that make it challenging for them to but not both. To address this, we introduce cooperate, it would be difficult to imagine that negotiation a targeted data acquisition framework where we could be useful to agents over time -- let alone society -- guide the exploration of a reinforcement learning if agents were incapable of cooperating to achieve equitable agent using annotations from an expert oracle.

Search is an important tool for computing effective policies in single- and multi-agent environments, and has been crucial for achieving superhuman performance in several benchmark fully and partially observable games. However, one major limitation of prior search approaches for partially observable environments is that the computational cost scales poorly with the amount of hidden information. In this paper we present \emph{Learned Belief Search} (LBS), a computationally efficient search procedure for partially observable environments. Rather than maintaining an exact belief distribution, LBS uses an approximate auto-regressive counterfactual belief that is learned as a supervised task. In multi-agent settings, LBS uses a novel public-private model architecture for underlying policies in order to efficiently evaluate these policies during rollouts. In the benchmark domain of Hanabi, LBS can obtain 55% ~ 91% of the benefit of exact search while reducing compute requirements by $35.8 \times$ ~ $4.6 \times$, allowing it to scale to larger settings that were inaccessible to previous search methods.

Language is an interface to the outside world. In order for embodied agents to use it, language must be grounded in other, sensorimotor modalities. While there is an extended literature studying how machines can learn grounded language, the topic of how to learn spatio-temporal linguistic concepts is still largely uncharted. To make progress in this direction, we here introduce a novel spatio-temporal language grounding task where the goal is to learn the meaning of spatio-temporal descriptions of behavioral traces of an embodied agent. This is achieved by training a truth function that predicts if a description matches a given history of observations. The descriptions involve time-extended predicates in past and present tense as well as spatio-temporal references to objects in the scene. To study the role of architectural biases in this task, we train several models including multimodal Transformer architectures; the latter implement different attention computations between words and objects across space and time. We test models on two classes of generalization: 1) generalization to randomly held-out sentences; 2) generalization to grammar primitives. We observe that maintaining object identity in the attention computation of our Transformers is instrumental to achieving good performance on generalization overall, and that summarizing object traces in a single token has little influence on performance. We then discuss how this opens new perspectives for language-guided autonomous embodied agents. We also release our code under open-source license as well as pretrained models and datasets to encourage the wider community to build upon and extend our work in the future.

The Association for the Advancement of Artificial Intelligence's 2021 Spring Symposium Series was held virtually from March 22-24, 2021. There were ten symposia in the program: Applied AI in Healthcare: Safety, Community, and the Environment, Artificial Intelligence for K-12 Education, Artificial Intelligence for Synthetic Biology, Challenges and Opportunities for Multi-Agent Reinforcement Learning, Combining Machine Learning and Knowledge Engineering, Combining Machine Learning with Physical Sciences, Implementing AI Ethics, Leveraging Systems Engineering to Realize Synergistic AI/Machine-Learning Capabilities, Machine Learning for Mobile Robot Navigation in the Wild, and Survival Prediction: Algorithms, Challenges and Applications. This report contains summaries of all the symposia. The two-day international virtual symposium included invited speakers, presenters of research papers, and breakout discussions from attendees around the world. Registrants were from different countries/cities including the US, Canada, Melbourne, Paris, Berlin, Lisbon, Beijing, Central America, Amsterdam, and Switzerland. We had active discussions about solving health-related, real-world issues in various emerging, ongoing, and underrepresented areas using innovative technologies including Artificial Intelligence and Robotics. We primarily focused on AI-assisted and robot-assisted healthcare, with specific focus on areas of improving safety, the community, and the environment through the latest technological advances in our respective fields. The day was kicked off by Raj Puri, Physician and Director of Strategic Health Initiatives & Innovation at Stanford University spoke about a novel, automated sentinel surveillance system his team built mitigating COVID and its integration into their public-facing dashboard of clinical data and metrics. Selected paper presentations during both days were wide ranging including talks from Oliver Bendel, a Professor from Switzerland and his Swiss colleague, Alina Gasser discussing co-robots in care and support, providing the latest information on technologies relating to human-robot interaction and communication. Yizheng Zhao, Associate Professor at Nanjing University and her colleagues from China discussed views of ontologies with applications to logical difference computation in the healthcare sector. Pooria Ghadiri from McGill University, Montreal, Canada discussed his research relating to AI enhancements in health-care delivery for adolescents with mental health problems in the primary care setting.

Inter-agent communication can significantly increase performance in multi-agent tasks that require co-ordination to achieve a shared goal. Prior work has shown that it is possible to learn inter-agent communication protocols using multi-agent reinforcement learning and message-passing network architectures. However, these models use an unconstrained broadcast communication model, in which an agent communicates with all other agents at every step, even when the task does not require it. In real-world applications, where communication may be limited by system constraints like bandwidth, power and network capacity, one might need to reduce the number of messages that are sent. In this work, we explore a simple method of minimizing communication while maximizing performance in multi-task learning: simultaneously optimizing a task-specific objective and a communication penalty. We show that the objectives can be optimized using Reinforce and the Gumbel-Softmax reparameterization. We introduce two techniques to stabilize training: 50% training and message forwarding. Training with the communication penalty on only 50% of the episodes prevents our models from turning off their outgoing messages. Second, repeating messages received previously helps models retain information, and further improves performance. With these techniques, we show that we can reduce communication by 75% with no loss of performance.

Artificial intelligence (AI) and robotic coaches promise the improved engagement of patients on rehabilitation exercises through social interaction. While previous work explored the potential of automatically monitoring exercises for AI and robotic coaches, the deployment of these systems remains a challenge. Previous work described the lack of involving stakeholders to design such functionalities as one of the major causes. In this paper, we present our efforts on eliciting the detailed design specifications on how AI and robotic coaches could interact with and guide patient's exercises in an effective and acceptable way with four therapists and five post-stroke survivors. Through iterative questionnaires and interviews, we found that both post-stroke survivors and therapists appreciated the potential benefits of AI and robotic coaches to achieve more systematic management and improve their self-efficacy and motivation on rehabilitation therapy. In addition, our evaluation sheds light on several practical concerns (e.g. a possible difficulty with the interaction for people with cognitive impairment, system failures, etc.). We discuss the value of early involvement of stakeholders and interactive techniques that complement system failures, but also support a personalized therapy session for the better deployment of AI and robotic exercise coaches.

The use of Artificial Intelligence (AI) for play-testing is still on the sidelines of main applications of AI in games compared to performance-oriented game-playing. One of the main purposes of play-testing a game is gathering data on the gameplay, highlighting good and bad features of the design of the game, providing useful insight to the game designers for improving the design. Using AI agents has the potential of speeding the process dramatically. The purpose of this research is to map the behavioural space (BSpace) of a game by using a general method. Using the MAP-Elites algorithm we search the hyperparameter space Rinascimento AI agents and map it to the BSpace defined by several behavioural metrics. This methodology was able to highlight both exemplary and degenerated behaviours in the original game design of Splendor and two variations. In particular, the use of event-value functions has generally shown a remarkable improvement in the coverage of the BSpace compared to agents based on classic score-based reward signals.

In real-world multi-agent systems, agents with different capabilities may join or leave without altering the team's overarching goals. Coordinating teams with such dynamic composition is challenging: the optimal team strategy varies with the composition. We propose COPA, a coach-player framework to tackle this problem. We assume the coach has a global view of the environment and coordinates the players, who only have partial views, by distributing individual strategies. Specifically, we 1) adopt the attention mechanism for both the coach and the players; 2) propose a variational objective to regularize learning; and 3) design an adaptive communication method to let the coach decide when to communicate with the players. We validate our methods on a resource collection task, a rescue game, and the StarCraft micromanagement tasks. We demonstrate zero-shot generalization to new team compositions. Our method achieves comparable or better performance than the setting where all players have a full view of the environment. Moreover, we see that the performance remains high even when the coach communicates as little as 13% of the time using the adaptive communication strategy.

Artificial Intelligence (AI) started out with an ambition to reproduce the human mind, but, as the sheer scale of that ambition became manifest, it quickly retreated into either studying specialized intelligent behaviours, or proposing over-arching architectural concepts for interfacing specialized intelligent behaviour components, conceived of as agents in a kind of organization. This agent-based modeling paradigm, in turn, proves to have interesting applications in understanding, simulating, and predicting the behaviour of social and legal structures on an aggregate level. For these reasons, this chapter examines a number of relevant cross-cutting concerns, conceptualizations, modeling problems and design challenges in large-scale distributed Artificial Intelligence, as well as in institutional systems, and identifies potential grounds for novel advances.