Collaborative multi-agent reinforcement learning (MARL) as a specific category of reinforcement learning provides effective results with agents learning from their observations, received rewards, and internal interactions between agents. However, centralized learning methods with a joint global policy in a highly dynamic environment present unique challenges in dealing with large amounts of information. This study proposes two innovative solutions to address the complexities of a collaboration between a human and multiple reinforcement learning (RL)-based agents (referred to thereafter as Human-MARL teaming) where the goals pursued cannot be achieved by a human alone or agents alone. The first innovation is the introduction of a new open-source MARL framework, called COGMENT, to unite humans and agents in real-time complex dynamic systems and efficiently leverage their interactions as a source of learning. The second innovation is our proposal of a new hybrid MARL method, named Dueling Double Deep Q learning MADDPG (D3-MADDPG) to allow agents to train decentralized policies parallelly in a joint centralized policy. This method can solve the overestimation problem in Q-learning methods of value-based MARL. We demonstrate these innovations by using a designed real-time environment with unmanned aerial vehicles driven by RL agents, collaborating with a human to fight fires. The team of RL agent drones autonomously look for fire seats and the human pilot douses the fires. The results of this study show that the proposed collaborative paradigm and the open-source framework leads to significant reductions in both human effort and exploration costs. Also, the results of the proposed hybrid MARL method shows that it effectively improves the learning process to achieve more reliable Q-values for each action, by decoupling the estimation between state value and advantage value.

It has long been recognized that multi-agent reinforcement learning (MARL) faces significant scalability issues due to the fact that the size of the state and action spaces are exponentially large in the number of agents. In this paper, we identify a rich class of networked MARL problems where the model exhibits a local dependence structure that allows it to be solved in a scalable manner. Specifically, we propose a Scalable Actor-Critic (SAC) method that can learn a near optimal localized policy for optimizing the average reward with complexity scaling with the state-action space size of local neighborhoods, as opposed to the entire network. Our result centers around identifying and exploiting an exponential decay property that ensures the effect of agents on each other decays exponentially fast in their graph distance.

Communication lays the foundation for human cooperation. It is also crucial for multi-agent cooperation. However, existing work focuses on broadcast communication, which is not only impractical but also leads to information redundancy that could even impair the learning process. To tackle these difficulties, we propose \textit{Individually Inferred Communication} (I2C), a simple yet effective model to enable agents to learn a prior for agent-agent communication. The prior knowledge is learned via causal inference and realized by a feed-forward neural network that maps the agent's local observation to a belief about who to communicate with. The influence of one agent on another is inferred via the joint action-value function in multi-agent reinforcement learning and quantified to label the necessity of agent-agent communication. Furthermore, the agent policy is regularized to better exploit communicated messages. Empirically, we show that I2C can not only reduce communication overhead but also improve the performance in a variety of multi-agent cooperative scenarios, comparing to existing methods.

Agent-based Models (ABMs) are valuable tools for policy analysis. ABMs help analysts explore the emergent consequences of policy interventions in multi-agent decision-making settings. But the validity of inferences drawn from ABM explorations depends on the quality of the ABM agents' behavioral models. Standard specifications of agent behavioral models rely either on heuristic decision-making rules or on regressions trained on past data. Both prior specification modes have limitations. This paper examines the value of reinforcement learning (RL) models as adaptive, high-performing, and behaviorally-valid models of agent decision-making in ABMs. We test the hypothesis that RL agents are effective as utility-maximizing agents in policy ABMs. We also address the problem of adapting RL algorithms to handle multi-agency in games by adapting and extending methods from recent literature. We evaluate the performance of such RL-based ABM agents via experiments on two policy-relevant ABMs: a minority game ABM, and an ABM of Influenza Transmission. We run some analytic experiments on our AI-equipped ABMs e.g. explorations of the effects of behavioral heterogeneity in a population and the emergence of synchronization in a population. The experiments show that RL behavioral models are effective at producing reward-seeking or reward-maximizing behaviors in ABM agents. Furthermore, RL behavioral models can learn to outperform the default adaptive behavioral models in the two ABMs examined.

Real world multi-agent tasks often involve varying types and quantities of agents and non-agent entities. Agents frequently do not know a priori how many other agents and non-agent entities they will need to interact with in order to complete a given task, requiring agents to generalize across a combinatorial number of task configurations with each potentially requiring different strategies. In this work, we tackle the problem of multi-agent reinforcement learning (MARL) in such dynamic scenarios. We hypothesize that, while the optimal behaviors in these scenarios with varying quantities and types of agents/entities are diverse, they may share common patterns within sub-teams of agents that are combined to form team behavior. As such, we propose a method that can learn these subgroup relationships and how they can be combined, ultimately improving knowledge sharing and generalization across scenarios. This method, Attentive-Imaginative QMIX, extends QMIX for dynamic MARL in two ways: 1) an attention mechanism that enables model sharing across variable sized scenarios and 2) a training objective that improves learning across scenarios with varying combinations of agent/entity types by factoring the value function into imagined sub-scenarios. We validate our approach on both a novel grid-world task as well as a version of the StarCraft Multi-Agent Challenge [28] minimally modified for the dynamic scenario setting.

We develop a mathematical framework for solving multi-task reinforcement learning problems based on a type of decentralized policy gradient method. The goal in multi-task reinforcement learning is to learn a common policy that operates effectively in different environments; these environments have similar (or overlapping) state and action spaces, but have different rewards and dynamics. Agents immersed in each of these environments communicate with other agents by sharing their models (i.e. their policy parameterizations) but not their state/reward paths. Our analysis provides a convergence rate for a consensus-based distributed, entropy-regularized policy gradient method for finding such a policy. We demonstrate the effectiveness of the proposed method using a series of numerical experiments. These experiments range from small-scale "Grid World" problems that readily demonstrate the trade-offs involved in multi-task learning to large-scale problems, where common policies are learned to play multiple Atari games or to navigate an airborne drone in multiple (simulated) environments.

We address the challenge of learning factored policies in cooperative MARL scenarios. In particular, we consider the situation in which a team of agents collaborates to optimize a common cost. Our goal is to obtain factored policies that determine the individual behavior of each agent so that the resulting joint policy is optimal. In this work we make contributions to both the dynamic programming and reinforcement learning settings. In the dynamic programming case we provide a number of lemmas that prove the existence of such factored policies and we introduce an algorithm (along with proof of convergence) that provably leads to them. Then we introduce tabular and deep versions of Logical Team Q-learning, which is a stochastic version of the algorithm for the RL case. We conclude the paper by providing experiments that illustrate the claims.

In such networks, symbiosis leads to socioeconomic and environmental benefits for involved industrial agents and the society (see [14, 39]). One barrier against stable ISN implementations is the lack of frameworks able to secure such networks against unfair and unstable allocation of obtainable benefits among the involved industrial firms. In other words, although in general ISNs result in the reduction of the total cost, a remaining challenge for operationalization of ISNs is to tailor reasonable mechanisms for allocating the total obtainable cost reductions--in a fair and stable manner--among the contributing firms. Otherwise, even if economic benefits are foreseeable, lack of stability and/or fairness may lead to non-cooperative decisions. This will be the main focus of what we call the industrial symbiosis implementation problem. Reviewing recent contributions in the field of industrial symbiosis research, we encounter studies focusing on the necessity to consider interrelations between industrial enterprises [43, 47] and the role of contract settings in the process of ISN implementation [1, 44]. We believe that a missed element for shifting from theoretical ISN design to practical ISN implementation is to model, reason about, and support ISN decision processes in a dynamic way (and not by using snapshotbased modeling frameworks). For such a multiagent setting, the mature field of cooperative game theory provides rigorous methodologies and established solution concepts, e.g. the core of the game and the Shapley allocation [15, 30, 34, 7]. However, for ISNs modeled as a cooperative game, these established solution concepts may be either non-feasible (due to properties of the game, e.g.

Multi-agent learning is a challenging problem in machine learning that has applications in different domains such as distributed control, robotics, and economics. We develop a prescriptive model of multi-agent behavior using Markov games. Since in many multi-agent systems, agents do not necessary select their optimum strategies against other agents (e.g., multi-pedestrian interaction), we focus on models in which the agents play "exploration but near optimum strategies". We model such policies using the Boltzmann-Gibbs distribution. This leads to a set of coupled Bellman equations that describes the behavior of the agents. We introduce a set of conditions under which the set of equations admit a unique solution and propose two algorithms that provably provide the solution in finite and infinite time horizon scenarios. We also study a practical setting in which the interactions can be described using the occupancy measures and propose a simplified Markov game with less complexity. Furthermore, we establish the connection between the Markov games with exploration strategies and the principle of maximum causal entropy for multi-agent systems. Finally, we evaluate the performance of our algorithms via several well-known games from the literature and some games that are designed based on real world applications.

Walk-based models have shown their unique advantages in knowledge graph (KG) reasoning by achieving state-of-the-art performance while allowing for explicit visualization of the decision sequence. However, the sparse reward signals offered by the KG during a traversal are often insufficient to guide a sophisticated reinforcement learning (RL) model. An alternate approach to KG reasoning is using traditional symbolic methods (e.g., rule induction), which achieve high precision without learning but are hard to generalize due to the limitation of symbolic representation. In this paper, we propose to fuse these two paradigms to get the best of both worlds. Our method leverages high-quality rules generated by symbolic-based methods to provide reward supervision for walk-based agents. Due to the structure of symbolic rules with their entity variables, we can separate our walk-based agent into two sub-agents thus allowing for additional efficiency. Experiments on public datasets demonstrate that walk-based models can benefit from rule guidance significantly.