It has been an open challenge for self-interested agents to make optimal sequential decisions in complex multiagent systems, where agents might achieve higher utility via collaboration. The Microsoft Malmo Collaborative AI Challenge (MCAC), which is designed to encourage research relating to various problems in Collaborative AI, takes the form of a Minecraft mini-game where players might work together to catch a pig or deviate from cooperation, for pursuing high scores to win the challenge. Various characteristics, such as complex interactions among agents, uncertainties, sequential decision making and limited learning trials all make it extremely challenging to find effective strategies. We present HogRider---the champion agent of MCAC in 2017 out of 81 teams from 26 countries. One key innovation of HogRider is a generalized agent type hypothesis framework to identify the behavior model of the other agents, which is demonstrated to be robust to observation uncertainty. On top of that, a second key innovation is a novel Q-learning approach to learn effective policies against each type of the collaborating agents. Various ideas are proposed to adapt traditional Q-learning to handle complexities in the challenge, including state-action abstraction to reduce problem scale, a warm start approach using human reasoning for addressing limited learning trials, and an active greedy strategy to balance exploitation-exploration. Challenge results show that HogRider outperforms all the other teams by a significant edge, in terms of both optimality and stability.

Observing that many real-world sequential decision problems are not purely cooperative or purely competitive, we propose a new model—cooperative-competitive process (CCP)—that can simultaneously encapsulate both cooperation and competition. First, we discuss how the CCP model bridges the gap between cooperative and competitive models. Next, we investigate a specific class of group-dominant CCPs, in which agents cooperate to achieve a common goal as their primary objective, while also pursuing individual goals as a secondary objective. We provide an approximate solution for this class of problems that leverages stochastic finite-state controllers. The model is grounded in two multi-robot meeting and box-pushing domains that are implemented in simulation and demonstrated on two real robots.

Although multi-agent reinforcement learning can tackle systems of strategically interacting entities, it currently fails in scalability and lacks rigorous convergence guarantees. Crucially, learning in multi-agent systems can become intractable due to the explosion in the size of the state-action space as the number of agents increases. In this paper, we propose a method for computing closed-loop optimal policies in multi-agent systems that scales independently of the number of agents. This allows us to show, for the first time, successful convergence to optimal behaviour in systems with an unbounded number of interacting adaptive learners. Studying the asymptotic regime of N-player stochastic games, we devise a learning protocol that is guaranteed to converge to equilibrium policies even when the number of agents is extremely large. Our method is model-free and completely decentralised so that each agent need only observe its local state information and its realised rewards. We validate these theoretical results by showing convergence to Nash-equilibrium policies in applications from economics and control theory with thousands of strategically interacting agents.

Resource constraints frequently complicate multi-agent planning problems. Existing algorithms for resource-constrained, multi-agent planning problems rely on the assumption that the constraints are deterministic. However, frequently resource constraints are themselves subject to uncertainty from external influences. Uncertainty about constraints is especially challenging when agents must execute in an environment where communication is unreliable, making on-line coordination difficult. In those cases, it is a significant challenge to find coordinated allocations at plan time depending on availability at run time. To address these limitations, we propose to extend algorithms for constrained multi-agent planning problems to handle stochastic resource constraints. We show how to factorize resource limit uncertainty and use this to develop novel algorithms to plan policies for stochastic constraints. We evaluate the algorithms on a search-and-rescue problem and on a power-constrained planning domain where the resource constraints are decided by nature. We show that plans taking into account all potential realizations of the constraint obtain significantly better utility than planning for the expectation, while causing fewer constraint violations.

Many real-world problems, such as network packet routing and the coordination of autonomous vehicles, are naturally modelled as cooperative multi-agent systems. There is a great need for new reinforcement learning methods that can efficiently learn decentralised policies for such systems. To this end, we propose a new multi-agent actor-critic method called counterfactual multi-agent (COMA) policy gradients. COMA uses a centralised critic to estimate the Q-function and decentralised actors to optimise the agents' policies. In addition, to address the challenges of multi-agent credit assignment, it uses a counterfactual baseline that marginalises out a single agent's action, while keeping the other agents' actions fixed. COMA also uses a critic representation that allows the counterfactual baseline to be computed efficiently in a single forward pass. We evaluate COMA in the testbed of StarCraft unit micromanagement, using a decentralised variant with significant partial observability. COMA significantly improves average performance over other multi-agent actor-critic methods in this setting, and the best performing agents are competitive with state-of-the-art centralised controllers that get access to the full state.

The meeting with Kagame comes not long after participants in a White House meeting said Trump had referred to African nations as "shitholes." And Trump has come under fire in Britain after he retweeted videos from a far-right British group and criticized London Mayor Sadiq Khan following a terror attack last year. Trump canceled plans for a recent trip to London to open the new $1 billion U.S. embassy there, a move that avoided protests promised by political opponents. The president said he skipped the trip because he was unhappy with the new embassy's cost and location.

The field of Multi-Agent System (MAS) is an active area of research within Artificial Intelligence, with an increasingly important impact in industrial and other real-world applications. Within a MAS, autonomous agents interact to pursue personal interests and/or to achieve common objectives. Distributed Constraint Optimization Problems (DCOPs) have emerged as one of the prominent agent architectures to govern the agents' autonomous behavior, where both algorithms and communication models are driven by the structure of the specific problem. During the last decade, several extensions to the DCOP model have enabled them to support MAS in complex, real-time, and uncertain environments. This survey aims at providing an overview of the DCOP model, giving a classification of its multiple extensions and addressing both resolution methods and applications that find a natural mapping within each class of DCOPs. The proposed classification suggests several future perspectives for DCOP extensions, and identifies challenges in the design of efficient resolution algorithms, possibly through the adaptation of strategies from different areas.

We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows. We then present an adaptation of actor-critic methods that considers action policies of other agents and is able to successfully learn policies that require complex multi-agent coordination. Additionally, we introduce a training regimen utilizing an ensemble of policies for each agent that leads to more robust multi-agent policies. We show the strength of our approach compared to existing methods in cooperative as well as competitive scenarios, where agent populations are able to discover various physical and informational coordination strategies.

Cooperative multi-agent systems can be naturally used to model many real world problems, such as network packet routing and the coordination of autonomous vehicles. There is a great need for new reinforcement learning methods that can efficiently learn decentralised policies for such systems. To this end, we propose a new multi-agent actor-critic method called counterfactual multi-agent (COMA) policy gradients. COMA uses a centralised critic to estimate the Q-function and decentralised actors to optimise the agents' policies. In addition, to address the challenges of multi-agent credit assignment, it uses a counterfactual baseline that marginalises out a single agent's action, while keeping the other agents' actions fixed. COMA also uses a critic representation that allows the counterfactual baseline to be computed efficiently in a single forward pass. We evaluate COMA in the testbed of StarCraft unit micromanagement, using a decentralised variant with significant partial observability. COMA significantly improves average performance over other multi-agent actor-critic methods in this setting, and the best performing agents are competitive with state-of-the-art centralised controllers that get access to the full state.

We propose a multiagent distributed actor-critic algorithm for multitask reinforcement learning (MRL), named Diff-DAC. The agents are connected, forming a (possibly sparse) network. Each agent is assigned a task and has access to data from this local task only. During the learning process, the agents are able to communicate some parameters to their neighbors. Since the agents incorporate their neighbors' parameters into their own learning rules, the information is diffused across the network, and they can learn a common policy that generalizes well across all tasks. Diff-DAC is scalable since the computational complexity and communication overhead per agent grow with the number of neighbors, rather than with the total number of agents. Moreover, the algorithm is fully distributed in the sense that agents self-organize, with no need for coordinator node. Diff-DAC follows an actor-critic scheme where the value function and the policy are approximated with deep neural networks, being able to learn expressive policies from raw data. As a by-product of Diff-DAC's derivation from duality theory, we provide novel insights into the standard actor-critic framework, showing that it is actually an instance of the dual ascent method to approximate the solution of a linear program. Experiments illustrate the performance of the algorithm in the cart-pole, inverted pendulum, and swing-up cart-pole environments.