Role-based learning holds the promise of achieving scalable multi-agent learning by decomposing complex tasks using roles. However, it is largely unclear how to efficiently discover such a set of roles. To solve this problem, we propose to first decompose joint action spaces into restricted role action spaces by clustering actions according to their effects on the environment and other agents. Learning a role selector based on action effects makes role discovery much easier because it forms a bi-level learning hierarchy -- the role selector searches in a smaller role space and at a lower temporal resolution, while role policies learn in significantly reduced primitive action-observation spaces. We further integrate information about action effects into the role policies to boost learning efficiency and policy generalization. By virtue of these advances, our method (1) outperforms the current state-of-the-art MARL algorithms on 10 of the 14 scenarios that comprise the challenging StarCraft II micromanagement benchmark and (2) achieves rapid transfer to new environments with three times the number of agents. Demonstrative videos are available at https://sites.google.com/view/rode-marl .

Multi-agent policy gradient (MAPG) methods recently witness vigorous progress. However, there is a significant performance discrepancy between MAPG methods and state-of-the-art multi-agent value-based approaches. In this paper, we investigate causes that hinder the performance of MAPG algorithms and present a multi-agent decomposed policy gradient method (DOP). This method introduces the idea of value function decomposition into the multi-agent actor-critic framework. Based on this idea, DOP supports efficient off-policy learning and addresses the issue of centralized-decentralized mismatch and credit assignment in both discrete and continuous action spaces. We formally show that DOP critics have sufficient representational capability to guarantee convergence. In addition, empirical evaluations on the StarCraft II micromanagement benchmark and multi-agent particle environments demonstrate that DOP significantly outperforms both state-of-the-art value-based and policy-based multi-agent reinforcement learning algorithms. Demonstrative videos are available at https://sites.google.com/view/dop-mapg/.

We consider the problem of learning to communicate using multi-agent reinforcement learning (MARL). A common approach is to learn off-policy, using data sampled from a replay buffer. However, messages received in the past may not accurately reflect the current communication policy of each agent, and this complicates learning. We therefore introduce a 'communication correction' which accounts for the non-stationarity of observed communication induced by multi-agent learning. It works by relabelling the received message to make it likely under the communicator's current policy, and thus be a better reflection of the receiver's current environment. To account for cases in which agents are both senders and receivers, we introduce an ordered relabelling scheme. Our correction is computationally efficient and can be integrated with a range of off-policy algorithms. It substantially improves the ability of communicating MARL systems to learn across a variety of cooperative and competitive tasks.

We propose a multi-agent based computational framework for modeling decision-making and strategic interaction at micro level for smart vehicles in a smart world. The concepts of Markov game and best response dynamics are heavily leveraged. Our aim is to make the framework conceptually sound and computationally practical for a range of realistic applications, including micro path planning for autonomous vehicles. To this end, we first convert the would-be stochastic game problem into a closely related deterministic one by introducing risk premium in the utility function for each individual agent. We show how the sub-game perfect Nash equilibrium of the simplified deterministic game can be solved by an algorithm based on best response dynamics. In order to better model human driving behaviors with bounded rationality, we seek to further simplify the solution concept by replacing the Nash equilibrium condition with a heuristic and adaptive optimization with finite look-ahead anticipation. In addition, the algorithm corresponding to the new solution concept drastically improves the computational efficiency. To demonstrate how our approach can be applied to realistic traffic settings, we conduct a simulation experiment: to derive merging and yielding behaviors on a double-lane highway with an unexpected barrier. Despite assumption differences involved in the two solution concepts, the derived numerical solutions show that the endogenized driving behaviors are very similar. We also briefly comment on how the proposed framework can be further extended in a number of directions in our forthcoming work, such as behavioral calibration using real traffic video data, computational mechanism design for traffic policy optimization, and so on.

We study a dynamic version of multi-agent path finding problem (called D-MAPF) where existing agents may leave and new agents may join the team at different times. We introduce a new method to solve D-MAPF based on conflict-resolution. The idea is, when a set of new agents joins the team and there are conflicts, instead of replanning for the whole team, to replan only for a minimal subset of agents whose plans conflict with each other. We utilize answer set programming as part of our method for planning, replanning and identifying minimal set of conflicts.

Recent progress in Game AI has demonstrated that given enough data from human gameplay, or experience gained via simulations, machines can rival or surpass the most skilled human players in classic games such as Go, or commercial computer games such as Starcraft. We review the current state-of-the-art through the lens of wargaming, and ask firstly what features of wargames distinguish them from the usual AI testbeds, and secondly which recent AI advances are best suited to address these wargame-specific features.

For prediction of interacting agents' trajectories, we propose an end-to-end trainable architecture that hybridizes neural nets with game-theoretic reasoning, has interpretable intermediate representations, and transfers to robust downstream decision making. It combines (1) a differentiable implicit layer that maps preferences to local Nash equilibria with (2) a learned equilibrium refinement concept and (3) a learned preference revelation net, given initial trajectories as input. This is accompanied by a new class of continuous potential games. We provide theoretical results for explicit gradients and soundness, and several measures to ensure tractability. In experiments, we evaluate our approach on two real-world data sets, where we predict highway driver merging trajectories, and on a simple decision-making transfer task.

We live in a challenging world particularly since the start of the Covid-19 pandemic. Our ways of living, communicating, interacting, purchasing, and working have changed. With every challenge comes great opportunity so I remain extremely optimistic about the outcomes of this crisis. During confinement, we got to know our neighbors better and offered assistance. We saw some great collaboration amongst colleagues.

We propose a novel method for expediting both symmetric and asymmetric Distributed Constraint Optimization Problem (DCOP) solvers. The core idea is based on initializing DCOP solvers with greedy fast non-iterative DCOP solvers. This is contrary to existing methods where initialization is always achieved using a random value assignment. We empirically show that changing the starting conditions of existing DCOP solvers not only reduces the algorithm convergence time by up to 50\%, but also reduces the communication overhead and leads to a better solution quality. We show that this effect is due to structural improvements in the variable assignment, which is caused by the spreading pattern of DCOP algorithm activation.) /Subject (Hybrid DCOPs)

Distributed Constraint Optimization Problems (DCOPs) are a widely studied class of optimization problems in which interaction between a set of cooperative agents are modeled as a set of constraints. DCOPs are NP-hard and significant effort has been devoted to developing methods for finding incomplete solutions. In this paper, we study an emerging class of such incomplete algorithms that are broadly termed as population-based algorithms. The main characteristic of these algorithms is that they maintain a population of candidate solutions of a given problem and use this population to cover a large area of the search space and to avoid local-optima. In recent years, this class of algorithms has gained significant attention due to their ability to produce high-quality incomplete solutions. With the primary goal of further improving the quality of solutions compared to the state-of-the-art incomplete DCOP algorithms, we present two new population-based algorithms in this paper. Our first approach, Anytime Evolutionary DCOP or AED, exploits evolutionary optimization meta-heuristics to solve DCOPs. We also present a novel anytime update mechanism that gives AED its anytime property. While in our second contribution, we show that population-based approaches can be combined with local search approaches. Specifically, we develop an algorithm called DPSA based on the Simulated Annealing meta-heuristic. We empirically evaluate these two algorithms to illustrate their respective effectiveness in different settings against the state-of-the-art incomplete DCOP algorithms including all existing population-based algorithms in a wide variety of benchmarks. Our evaluation shows AED and DPSA markedly outperform the state-of-the-art and produce up to 75% improved solutions.