NeurIPS 2022 论文列表

We introduce an offline multi-agent reinforcement learning ( offline MARL) framework that utilizes previously collected data without additional online data collection. Our method reformulates offline MARL as a sequence modeling problem and thus builds on top of the simplicity and scalability of the Transformer architecture. In the fashion of centralized training and decentralized execution, we propose to first train a teacher policy as if the MARL dataset is generated by a single agent. After the teacher policy has identified and recombined the "good" behavior in the dataset, we create separate student policies and distill not only the teacher policy's features but also its structural relations among different agents' features to student policies. Despite its simplicity, the proposed method outperforms state-of-the-art model-free offline MARL baselines while being more robust to demonstration's quality on several environments.

In cooperative multi-agent reinforcement learning, centralized training and decentralized execution (CTDE) has achieved remarkable success. Individual Global Max (IGM) decomposition, which is an important element of CTDE, measures the consistency between local and joint policies. The majority of IGM-based research focuses on how to establish this consistent relationship, but little attention has been paid to examining IGM's potential flaws. In this work, we reveal that the IGM condition is a lossy decomposition, and the error of lossy decomposition will accumulated in hypernetwork-based methods. To address the above issue, we propose to adopt an imitation learning strategy to separate the lossy decomposition from Bellman iterations, thereby avoiding error accumulation. The proposed strategy is theoretically proved and empirically verified on the StarCraft Multi-Agent Challenge benchmark problem with zero sight view. The results also confirm that the proposed method outperforms state-of-the-art IGM-based approaches.

Fully decentralized multi-agent reinforcement learning has shown great potentials for many real-world cooperative tasks, where the global information, \textit{e.g.}, the actions of other agents, is not accessible. Although independent Q-learning is widely used for decentralized training, the transition probabilities are non-stationary since other agents are updating policies simultaneously, which leads to non-guaranteed convergence of independent Q-learning. To deal with non-stationarity, we first introduce stationary ideal transition probabilities, on which independent Q-learning could converge to the global optimum. Further, we propose a fully decentralized method, I2Q, which performs independent Q-learning on the modeled ideal transition function to reach the global optimum. The modeling of ideal transition function in I2Q is fully decentralized and independent from the learned policies of other agents, helping I2Q be free from non-stationarity and learn the optimal policy. Empirically, we show that I2Q can achieve remarkable improvement in a variety of cooperative multi-agent tasks.

This paper considers offline multi-agent reinforcement learning. We propose the strategy-wise concentration principle which directly builds a confidence interval for the joint strategy, in contrast to the point-wise concentration principle which builds a confidence interval for each point in the joint action space. For two-player zero-sum Markov games, by exploiting the convexity of the strategy-wise bonus, we propose a computationally efficient algorithm whose sample complexity enjoys a better dependency on the number of actions than the prior methods based on the point-wise bonus. Furthermore, for offline multi-agent general-sum Markov games, based on the strategy-wise bonus and a novel surrogate function, we give the first algorithm whose sample complexity only scales $\sum_{i=1}^m A_i$ where $A_i$ is the action size of the $i$-th player and $m$ is the number of players. In sharp contrast, the sample complexity of methods based on the point-wise bonus would scale with the size of the joint action space $\Pi_{i=1}^m A_i$ due to the curse of multiagents. Lastly, all of our algorithms can naturally take a pre-specified strategy class $\Pi$ as input and output a strategy that is close to the best strategy in $\Pi$. In this setting, the sample complexity only scales with $\log |\Pi|$ instead of $\sum_{i=1}^m A_i$.

Multi-Agent Reinforcement Learning (MARL) has demonstrated significant suc2 cess by virtue of collaboration across agents. Recent work, on the other hand, introduces surprise which quantifies the degree of change in an agent’s environ4 ment. Surprise-based learning has received significant attention in the case of single-agent entropic settings but remains an open problem for fast-paced dynamics in multi-agent scenarios. A potential alternative to address surprise may be realized through the lens of free-energy minimization. We explore surprise minimization in multi-agent learning by utilizing the free energy across all agents in a multi-agent system. A temporal Energy-Based Model (EBM) represents an estimate of surprise which is minimized over the joint agent distribution. Our formulation of the EBM is theoretically akin to the minimum conjugate entropy objective and highlights suitable convergence towards minimum surprising states. We further validate our theoretical claims in an empirical study of multi-agent tasks demanding collabora14 tion in the presence of fast-paced dynamics. Our implementation and agent videos are available at the Project Webpage.

We consider a scenario where multiple agents are learning a common decision vector from data which can be influenced by the agents’ decisions. This leads to the problem of multi-agent performative prediction (Multi-PfD). In this paper, we formulate Multi-PfD as a decentralized optimization problem that minimizes a sum of loss functions, where each loss function is based on a distribution influenced by the local decision vector. We first prove the necessary and sufficient condition for the Multi-PfD problem to admit a unique multi-agent performative stable (Multi-PS) solution. We show that enforcing consensus leads to a laxer condition for existence of Multi-PS solution with respect to the distributions’ sensitivities, compared to the single agent case. Then, we study a decentralized extension to  the greedy deployment scheme [Mendler-Dünner et al., 2020], called the DSGD-GD  scheme. We show that DSGD-GD converges to the Multi-PS solution and analyze its non asymptotic convergence rate. Numerical results validate our analysis.

Modern multi-agent reinforcement learning frameworks rely on centralized training and reward shaping to perform well. However, centralized training and dense rewards are not readily available in the real world. Current multi-agent algorithms struggle to learn in the alternative setup of decentralized training or sparse rewards. To address these issues, we propose a self-supervised intrinsic reward \textit{ELIGN - expectation alignment - } inspired by the self-organization principle in Zoology. Similar to how animals collaborate in a decentralized manner with those in their vicinity, agents trained with expectation alignment learn behaviors that match their neighbors' expectations. This allows the agents to learn collaborative behaviors without any external reward or centralized training. We demonstrate the efficacy of our approach across 6 tasks in the multi-agent particle and the complex Google Research football environments, comparing ELIGN to sparse and curiosity-based intrinsic rewards. When the number of agents increases, ELIGN scales well in all multi-agent tasks except for one where agents have different capabilities. We show that agent coordination improves through expectation alignment because agents learn to divide tasks amongst themselves, break coordination symmetries, and confuse adversaries. These results identify tasks where expectation alignment is a more useful strategy than curiosity-driven exploration for multi-agent coordination, enabling agents to do zero-shot coordination.

Understanding human tasks through video observations is an essential capability of intelligent agents. The challenges of such capability lie in the difficulty of generating a detailed understanding of situated actions, their effects on object states (\ie, state changes), and their causal dependencies. These challenges are further aggravated by the natural parallelism from multi-tasking and partial observations in multi-agent collaboration. Most prior works leverage action localization or future prediction as an \textit{indirect} metric for evaluating such task understanding from videos. To make a \textit{direct} evaluation, we introduce the EgoTaskQA benchmark that provides a single home for the crucial dimensions of task understanding through question answering on real-world egocentric videos. We meticulously design questions that target the understanding of (1) action dependencies and effects, (2) intents and goals, and (3) agents' beliefs about others. These questions are divided into four types, including descriptive (what status?), predictive (what will?), explanatory (what caused?), and counterfactual (what if?) to provide diagnostic analyses on \textit{spatial, temporal, and causal} understandings of goal-oriented tasks. We evaluate state-of-the-art video reasoning models on our benchmark and show their significant gaps between humans in understanding complex goal-oriented egocentric videos. We hope this effort would drive the vision community to move onward with goal-oriented video understanding and reasoning.

This paper investigates the network load balancing problem in data centers (DCs) where multiple load balancers (LBs) are deployed, using the multi-agent reinforcement learning (MARL) framework. The challenges of this problem consist of the heterogeneous processing architecture and dynamic environments, as well as limited and partial observability of each LB agent in distributed networking systems, which can largely degrade the performance of in-production load balancing algorithms in real-world setups. Centralised training and distributed execution (CTDE) RL scheme has been proposed to improve MARL performance, yet it incurs -- especially in distributed networking systems, which prefer distributed and plug-and-play design schemes -- additional communication and management overhead among agents. We formulate the multi-agent load balancing problem as a Markov potential game, with a carefully and properly designed workload distribution fairness as the potential function. A fully distributed MARL algorithm is proposed to approximate the Nash equilibrium of the game. Experimental evaluations involve both an event-driven simulator and a real-world system, where the proposed MARL load balancing algorithm shows close-to-optimal performance in simulations and superior results over in-production LBs in the real-world system.

Utilizing messages from teammates can improve coordination in cooperative Multi-agent Reinforcement Learning (MARL). To obtain meaningful information for decision-making, previous works typically combine raw messages generated by teammates with local information as inputs for policy. However, neglecting the aggregation of multiple messages poses great inefficiency for policy learning. Motivated by recent advances in representation learning, we argue that efficient message aggregation is essential for good coordination in MARL. In this paper, we propose Multi-Agent communication via Self-supervised Information Aggregation (MASIA), with which agents can aggregate the received messages into compact representations with high relevance to augment the local policy. Specifically, we design a permutation invariant message encoder to generate common information aggregated representation from raw messages and optimize it via reconstructing and shooting future information in a self-supervised manner. Each agent would utilize the most relevant parts of the aggregated representation for decision-making by a novel message extraction mechanism. Empirical results demonstrate that our method significantly outperforms strong baselines on multiple cooperative MARL tasks for various task settings.

We study envy-free policy teaching. A number of agents independently explore a common Markov decision process (MDP), but each with their own reward function and discounting rate. A teacher wants to teach a target policy to this diverse group of agents, by means of modifying the agents' reward functions: providing additional bonuses to certain actions, or penalizing them. When personalized reward modification programs are used, an important question is how to design the programs so that the agents think they are treated fairly. We adopt the notion of envy-freeness (EF) from the literature on fair division to formalize this problem and investigate several fundamental questions about the existence of EF solutions in our setting, the computation of cost-minimizing solutions, as well as the price of fairness (PoF), which measures the increase of cost due to the consideration of fairness. We show that 1) an EF solution may not exist if penalties are not allowed in the modifications, but otherwise always exists. 2) Computing a cost-minimizing EF solution can be formulated as convex optimization and hence solved efficiently. 3) The PoF increases but at most quadratically with the geometric sum of the discount factor, and at most linearly with the size of the MDP and the number of agents involved; we present tight asymptotic bounds on the PoF. These results indicate that fairness can be incorporated in multi-agent teaching without significant computational or PoF burdens.

Due to its high sample complexity, simulation is, as of today, critical for the successful application of reinforcement learning. Many real-world problems, however, exhibit overly complex dynamics, making their full-scale simulation computationally slow. In this paper, we show how to factorize large networked systems of many agents into multiple local regions such that we can build separate simulators that run independently and in parallel. To monitor the influence that the different local regions exert on one another, each of these simulators is equipped with a learned model that is periodically trained on real trajectories. Our empirical results reveal that distributing the simulation among different processes not only makes it possible to train large multi-agent systems in just a few hours but also helps mitigate the negative effects of simultaneous learning.

Reinforcement learning typically relies heavily on a well-designed reward signal, which gets more challenging in cooperative multi-agent reinforcement learning. Alternatively, unsupervised reinforcement learning (URL) has delivered on its promise in the recent past to learn useful skills and explore the environment without external supervised signals. These approaches mainly aimed for the single agent to reach distinguishable states, insufficient for multi-agent systems due to that each agent interacts with not only the environment, but also the other agents. We propose Synergy Pattern Diversifying Oriented Unsupervised Multi-agent Reinforcement Learning (SPD) to learn generic coordination policies for agents with no extrinsic reward. Specifically, we devise the Synergy Pattern Graph (SPG), a graph depicting the relationships of agents at each time step. Furthermore, we propose an episode-wise divergence measurement to approximate the discrepancy of synergy patterns. To overcome the challenge of sparse return, we decompose the discrepancy of synergy patterns to per-time-step pseudo-reward. Empirically, we show the capacity of SPD to acquire meaningful coordination policies, such as maintaining specific formations in Multi-Agent Particle Environment and pass-and-shoot in Google Research Football. Furthermore, we demonstrate that the same instructive pretrained policy's parameters can serve as a good initialization for a series of downstream tasks' policies, achieving higher data efficiency and outperforming state-of-the-art approaches in Google Research Football.

Centralized training with decentralized execution (CTDE) has achieved great success in cooperative multi-agent reinforcement learning (MARL) in practical applications. However, CTDE-based methods typically suffer from poor zero-shot generalization ability with dynamic team composition and varying partial observability. To tackle these issues, we propose a spontaneously grouping mechanism, termed Self-Organized Group (SOG), which is featured with conductor election (CE) and message summary (MS). In CE, a certain number of conductors are elected every $T$ time-steps to temporally construct groups, each with conductor-follower consensus where the followers are constrained to only communicate with their conductor. In MS, each conductor summarize and distribute the received messages to all affiliate group members to hold a unified scheduling. SOG provides zero-shot generalization ability to the dynamic number of agents and the varying partial observability. Sufficient experiments on mainstream multi-agent benchmarks exhibit superiority of SOG.

Automated algorithm configuration relieves users from tedious, trial-and-error tuning tasks. A popular algorithm configuration tuning paradigm is dynamic algorithm configuration (DAC), in which an agent learns dynamic configuration policies across instances by reinforcement learning (RL). However, in many complex algorithms, there may exist different types of configuration hyperparameters, and such heterogeneity may bring difficulties for classic DAC which uses a single-agent RL policy. In this paper, we aim to address this issue and propose multi-agent DAC (MA-DAC), with one agent working for one type of configuration hyperparameter. MA-DAC formulates the dynamic configuration of a complex algorithm with multiple types of hyperparameters as a contextual multi-agent Markov decision process and solves it by a cooperative multi-agent RL (MARL) algorithm. To instantiate, we apply MA-DAC to a well-known optimization algorithm for multi-objective optimization problems. Experimental results show the effectiveness of MA-DAC in not only achieving superior performance compared with other configuration tuning approaches based on heuristic rules, multi-armed bandits, and single-agent RL, but also being capable of generalizing to different problem classes. Furthermore, we release the environments in this paper as a benchmark for testing MARL algorithms, with the hope of facilitating the application of MARL.

Recently, model-based agents have achieved better performance than model-free ones using the same computational budget and training time in single-agent environments. However, due to the complexity of multi-agent systems, it is tough to learn the model of the environment. The significant compounding error may hinder the learning process when model-based methods are applied to multi-agent tasks. This paper proposes an implicit model-based multi-agent reinforcement learning method based on value decomposition methods. Under this method, agents can interact with the learned virtual environment and evaluate the current state value according to imagined future states in the latent space, making agents have the foresight. Our approach can be applied to any multi-agent value decomposition method. The experimental results show that our method improves the sample efficiency in different partially observable Markov decision process domains.

Multi-agent collaborative perception could significantly upgrade the perception performance by enabling agents to share complementary information with each other through communication. It inevitably results in a fundamental trade-off between perception performance and communication bandwidth. To tackle this bottleneck issue, we propose a spatial confidence map, which reflects the spatial heterogeneity of perceptual information. It empowers agents to only share spatially sparse, yet perceptually critical information, contributing to where to communicate. Based on this novel spatial confidence map, we propose Where2comm, a communication-efficient collaborative perception framework. Where2comm has two distinct advantages: i) it considers pragmatic compression and uses less communication to achieve higher perception performance by focusing on perceptually critical areas; and ii) it can handle varying communication bandwidth by dynamically adjusting spatial areas involved in communication. To evaluate Where2comm, we consider 3D object detection in both real-world and simulation scenarios with two modalities (camera/LiDAR) and two agent types (cars/drones) on four datasets: OPV2V, V2X-Sim, DAIR-V2X, and our original CoPerception-UAVs. Where2comm consistently outperforms previous methods; for example, it achieves more than $100,000 \times$ lower communication volume and still outperforms DiscoNet and V2X-ViT on OPV2V. Our code is available at~\url{https://github.com/MediaBrain-SJTU/where2comm}.

The factorization of state-action value functions for Multi-Agent Reinforcement Learning (MARL) is important. Existing studies are limited by their representation capability, sample efficiency, and approximation error. To address these challenges, we propose, ResQ, a MARL value function factorization method, which can find the optimal joint policy for any state-action value function through residual functions. ResQ masks some state-action value pairs from a joint state-action value function, which is transformed as the sum of a main function and a residual function. ResQ can be used with mean-value and stochastic-value RL. We theoretically show that ResQ can satisfy both the individual global max (IGM) and the distributional IGM principle without representation limitations. Through experiments on matrix games, the predator-prey, and StarCraft benchmarks, we show that ResQ can obtain better results than multiple expected/stochastic value factorization methods.

Allowing agents to share information through communication is crucial for solving complex tasks in multi-agent reinforcement learning. In this work, we consider the question of whether a given communication protocol can express an arbitrary policy. By observing that many existing protocols can be viewed as instances of graph neural networks (GNNs), we demonstrate the equivalence of joint action selection to node labelling. With standard GNN approaches provably limited in their expressive capacity, we draw from existing GNN literature and consider augmenting agent observations with: (1) unique agent IDs and (2) random noise. We provide a theoretical analysis as to how these approaches yield universally expressive communication, and also prove them capable of targeting arbitrary sets of actions for identical agents. Empirically, these augmentations are found to improve performance on tasks where expressive communication is required, whilst, in general, the optimal communication protocol is found to be task-dependent.