Multiagent reinforcement learning (MARL) has been widely investigated, ranging from theoretical analysis to real-life applications. However, the utilization of existing non-transparent neural network architectures has resulted in opaque decision-making processes, making it difficult for humans to understand and trust the models being used. Fundamentally, all data is a topological structure, which provides reliable transparency for MARL tasks due to its powerful relational expression capability, scalability, and explicit structural relationships. In this article, we propose a novel approach of graph cooperation modeling (GCM), explicitly capturing and comprehending the complex dynamics of collaborative relationships among agents with the graph structure. GCM learns a metric function to discern beneficial interactions among agents, integrating it into the agent aggregation strategy of a graph neural network (GNN) capable of modeling arbitrary-order interactions. Furthermore, GCM utilizes identity semantics together with global state and individual value functions to estimate the credit of each agent, enhancing each agent's distinct focus on task-related regions. Extensive experiments on a range of challenging MARL benchmarks demonstrate that GCM not only delivers up to 28.75% relative performance gains on super-hard maps but also offers clear interpretability that provides insights into the underlying cooperative patterns.

The ability to model interactions among agents is crucial for effective coordination and understanding their cooperation mechanisms in multi-agent reinforcement learning (MARL). However, previous efforts to model high-order interactions have been primarily hindered by the combinatorial explosion or the opaque nature of their black-box network structures. In this paper, we propose a novel value decomposition framework, called Continued Fraction Q-Learning (QCoFr), which can flexibly capture arbitrary-order agent interactions with only linear complexity $\mathcal{O}\left({n}\right)$ in the number of agents, thus avoiding the combinatorial explosion when modeling rich cooperation. Furthermore, we introduce the variational information bottleneck to extract latent information for estimating credits. This latent information helps agents filter out noisy interactions, thereby significantly enhancing both cooperation and interpretability. Extensive experiments demonstrate that QCoFr not only consistently achieves better performance but also provides interpretability that aligns with our theoretical analysis.

Efficient exploration in multi-agent reinforcement learning (MARL) is a challenging problem when receiving only a team reward, especially in environments with sparse rewards. A powerful method to mitigate this issue involves crafting dense individual rewards to guide the agents toward efficient exploration. However, individual rewards generally rely on manually engineered shaping-reward functions that lack high-order intelligence, thus it behaves ineffectively than humans regarding learning and generalization in complex problems. To tackle these issues, we combine the above two paradigms and propose a novel framework, LIGHT (Learning Individual Intrinsic reward via Incorporating Generalized Human experTise), which can integrate human knowledge into MARL algorithms in an end-to-end manner. LIGHT guides each agent to avoid unnecessary exploration by considering both individual action distribution and human expertise preference distribution. Then, LIGHT designs individual intrinsic rewards for each agent based on actionable representational transformation relevant to Q-learning so that the agents align their action preferences with the human expertise while maximizing the joint action value. Experimental results demonstrate the superiority of our method over representative baselines regarding performance and better knowledge reusability across different sparse-reward tasks on challenging scenarios.

Time geography is an elegant framework for analyzing human activity–travel behaviors across temporal and spatial dimensions. At the core of this framework are the concepts of space–time paths, which represent historical trajectories, and space–time prisms, which define potential future activity spaces. However, most studies examine space–time paths and prisms in isolation, overlooking the integrative nature of time geography as a theoretical framework that incorporates the past, present, and future within a continuous temporal dimension. This study addresses this gap by developing novel methods for measuring and querying the spatiotemporal proximity of these heterogeneous and heterochronous time-geographic entities. To operationalize these methods, a GIS tool was implemented to support the local density analysis of time-geographic entities. Comprehensive computational experiments were conducted to validate the developed methods using large-scale, network-constrained, and time-geographic datasets. The developed methods exhibited high computational efficiency (approximately 2 s) in computing the local density for each path within extensive prism collections. The experimental results demonstrate the effectiveness of the developed methods in analyzing and visualizing the local density of historical paths in the near future. The methods offer new insights into space–time interactions, advancing research in human mobility forecasting and spatial decision-making.