A gossip protocol is a procedure for sharing secrets in a network. The basic action in a gossip protocol is a telephone call wherein the calling agents exchange all the secrets they know. An agent who knows all secrets is an expert. The usual termination condition is that all agents are experts. Instead, we explore protocols wherein the termination condition is that all agents know that all agents are experts. We call such agents super experts. Additionally, we model that agents who are super experts do not make and do not answer calls. Such agents are called engaged agents. We also model that such gossip protocols are common knowledge among the agents. We investigate conditions under which protocols terminate, both in the synchronous case, where there is a global clock, and in the asynchronous case, where there is not. We show that a commonly known protocol with engaged agents may terminate faster than the same protocol without engaged agents.

We study strategic network formation games in which agents attempt to form (costly) links in order to maximize their network centrality. Our model derives from Jackson and Wolinsky's symmetric connection model, but allows for heterogeneity in agent utilities by replacing decay centrality (implicit in the Jackson-Wolinsky model) by a variety of classical centrality and game-theoretic measures of centrality. We are primarily interested in characterizing the asymptotically pairwise stable networks, i.e. those networks that are pairwise stable for all sufficiently small, positive edge costs. We uncover a rich typology of stability: - we give an axiomatic approach to network centrality that allows us to predict the stable network for a rich set of combination of centrality utility functions, yielding stable networks with features reminiscent of structural properties such as "core periphery" and "rich club" networks. - We show that a simple variation on the model renders it universal, i.e. every network may be a stable network. - We also show that often we can infer a significant amount about agent utilities from the structure of stable networks.

The domains of transport and logistics are increasingly relying on autonomous mobile robots for the handling and distribution of passengers or resources. At large system scales, finding decentralized path planning and coordination solutions is key to efficient system performance. Recently, Graph Neural Networks (GNNs) have become popular due to their ability to learn communication policies in decentralized multi-agent systems. Yet, vanilla GNNs rely on simplistic message aggregation mechanisms that prevent agents from prioritizing important information. To tackle this challenge, in this paper, we extend our previous work that utilizes GNNs in multi-agent path planning by incorporating a novel mechanism to allow for message-dependent attention. Our Message-Aware Graph Attention neTwork (MAGAT) is based on a key-query-like mechanism that determines the relative importance of features in the messages received from various neighboring robots. We show that MAGAT is able to achieve a performance close to that of a coupled centralized expert algorithm. Further, ablation studies and comparisons to several benchmark models show that our attention mechanism is very effective across different robot densities and performs stably in different constraints in communication bandwidth. Experiments demonstrate that our model is able to generalize well in previously unseen problem instances, and it achieves a 47% improvement over the benchmark success rate, even in very large-scale instances that are 100x larger than the training instances.

Two-sided mobility platforms, such as Uber and Lyft, widely emerged in the urban mobility landscape, bringing disruptive changes to transportation systems worldwide. This calls for a simulation framework where researchers from various and across disciplines may introduce models aimed at representing the dynamics of platform-driven urban mobility systems. In this work, we present MaaSSim, an agent-based simulator reproducing the transport system used by two kind of agents: (i) travellers, requesting to travel from their origin to destination at a given time, and (ii) drivers supplying their travel needs by offering them rides. An intermediate agent, the platform, allows demand to be matched with supply. Agents are decision makers, specifically, travellers may decide which mode they use or reject an incoming offer. Similarly, drivers may opt-out from the system or reject incoming requests. All of the above behaviours are modelled through user-defined modules, representing agents' taste variations (heterogeneity), their previous experiences (learning) and available information (system control). MaaSSim is an open-source library available at a public repository github.com/RafalKucharskiPK/MaaSSim, along with a set of tutorials and reproducible use-case scenarios.

MOBA games, e.g., Honor of Kings, League of Legends, and Dota 2, pose grand challenges to AI systems such as multi-agent, enormous state-action space, complex action control, etc. Developing AI for playing MOBA games has raised much attention accordingly. However, existing work falls short in handling the raw game complexity caused by the explosion of agent combinations, i.e., lineups, when expanding the hero pool in case that OpenAI's Dota AI limits the play to a pool of only 17 heroes. As a result, full MOBA games without restrictions are far from being mastered by any existing AI system. In this paper, we propose a MOBA AI learning paradigm that methodologically enables playing full MOBA games with deep reinforcement learning. Specifically, we develop a combination of novel and existing learning techniques, including curriculum self-play learning, policy distillation, off-policy adaption, multi-head value estimation, and Monte-Carlo tree-search, in training and playing a large pool of heroes, meanwhile addressing the scalability issue skillfully. Tested on Honor of Kings, a popular MOBA game, we show how to build superhuman AI agents that can defeat top esports players. The superiority of our AI is demonstrated by the first large-scale performance test of MOBA AI agent in the literature.

We study a general class of entropy-regularized multi-variate LQG mean field games (MFGs) in continuous time with $K$ distinct sub-population of agents. We extend the notion of actions to action distributions (exploratory actions), and explicitly derive the optimal action distributions for individual agents in the limiting MFG. We demonstrate that the optimal set of action distributions yields an $\epsilon$-Nash equilibrium for the finite-population entropy-regularized MFG. Furthermore, we compare the resulting solutions with those of classical LQG MFGs and establish the equivalence of their existence.

As part of a new collaboration to advance and support AI research, the MIT Stephen A. Schwarzman College of Computing and the Defense Science and Technology Agency in Singapore are awarding funding to 13 projects led by researchers within the college that target one or more of the following themes: trustworthy AI, enhancing human cognition in complex environments, and AI for everyone. The 13 research projects selected are highlighted below. Emerging machine learning technology has the potential to significantly help with and even fully automate many tasks that have confidently been entrusted only to humans so far. Leveraging recent advances in realistic graphics rendering, data modeling, and inference, Madry's team is building a radically new toolbox to fuel streamlined development and deployment of trustworthy machine learning solutions. In natural language technologies, most languages in the world are not richly annotated.

Machine learning has the potential to aid in mitigating the human effects of climate change. Previous applications of machine learning to tackle the human effects in climate change include approaches like informing individuals of their carbon footprint and strategies to reduce it. For these methods to be the most effective they must consider relevant social-psychological factors for each individual. Of social-psychological factors at play in climate change, affect has been previously identified as a key element in perceptions and willingness to engage in mitigative behaviours. In this work, we propose an investigation into how affect could be incorporated to enhance machine learning based interventions for climate change. We propose using affective agent-based modelling for climate change as well as the use of a simulated climate change social dilemma to explore the potential benefits of affective machine learning interventions. Behavioural and informational interventions can be a powerful tool in helping humans adopt mitigative behaviours. We expect that utilizing affective ML can make interventions an even more powerful tool and help mitigative behaviours become widely adopted.

President-elect Joe Biden named John Kerry to the newly created role of climate czar, a move that underscores the incoming administration's commitment to an international-focused approach to the issue and recognition of its strategic importance. Kerry, the former secretary of state, is a diplomatic heavyweight who helped piece together the landmark Paris climate agreement during the Obama administration and pushed hard for domestic climate policies as a US senator. "I've asked him to return to government to get America back on track to address one of the most urgent national security threats we face--the climate crisis," Biden said in a statement released on Monday. "This role is the first of its kind: the first cabinet-level climate position, and the first time climate change has had a seat at the table on the National Security Council." Kerry's appointment as "special presidential envoy for climate" is among the first of six cabinet-level nominations that the Biden team announced on Monday, as it works to form a government in spite of President Donald Trump's refusal to accept the results of the election.

This paper introduces an information-theoretic constraint on learned policy complexity in the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) reinforcement learning algorithm. Previous research with a related approach in continuous control experiments suggests that this method favors learning policies that are more robust to changing environment dynamics. The multi-agent game setting naturally requires this type of robustness, as other agents' policies change throughout learning, introducing a nonstationary environment. For this reason, recent methods in continual learning are compared to our approach, termed Capacity-Limited MADDPG. Results from experimentation in multi-agent cooperative and competitive tasks demonstrate that the capacity-limited approach is a good candidate for improving learning performance in these environments.