Dapeng Li

Neng Wan, Dapeng Li, Naira Hovakimyan

A simplified approach is proposed to investigate the continuous-time and discrete-time complementary sensitivity Bode integrals (CSBIs) in this note. For continuous-time feedback systems with unbounded frequency domain, the CSBI weighted by $1/ω^2$ is considered, where this simplified method reveals a more explicit relationship between the value of CSBI and the structure of the open-loop transfer function. With a minor modification of this method, the CSBI of discrete-time system is derived, and illustrative examples are provided. Compared with the existing results on CSBI, neither Cauchy integral theorem nor Poisson integral formula are used throughout the analysis, and the analytic constraint on the integrand is removed.

Yuanjun Li, Bin Zhang, Hao Chen et al.

Value decomposition (VD) methods have achieved remarkable success in cooperative multi-agent reinforcement learning (MARL). However, their reliance on the max operator for temporal-difference (TD) target calculation leads to systematic Q-value overestimation. This issue is particularly severe in MARL due to the combinatorial explosion of the joint action space, which often results in unstable learning and suboptimal policies. To address this problem, we propose QSIM, a similarity weighted Q-learning framework that reconstructs the TD target using action similarity. Instead of using the greedy joint action directly, QSIM forms a similarity weighted expectation over a structured near-greedy joint action space. This formulation allows the target to integrate Q-values from diverse yet behaviorally related actions while assigning greater influence to those that are more similar to the greedy choice. By smoothing the target with structurally relevant alternatives, QSIM effectively mitigates overestimation and improves learning stability. Extensive experiments demonstrate that QSIM can be seamlessly integrated with various VD methods, consistently yielding superior performance and stability compared to the original algorithms. Furthermore, empirical analysis confirms that QSIM significantly mitigates the systematic value overestimation in MARL. Code is available at https://github.com/MaoMaoLYJ/pymarl-qsim.

Bin Zhang, Hangyu Mao, Jingqing Ruan et al.

The remarkable progress in Large Language Models (LLMs) opens up new avenues for addressing planning and decision-making problems in Multi-Agent Systems (MAS). However, as the number of agents increases, the issues of hallucination in LLMs and coordination in MAS have become increasingly prominent. Additionally, the efficient utilization of tokens emerges as a critical consideration when employing LLMs to facilitate the interactions among a substantial number of agents. In this paper, we develop a modular framework called LLaMAC to mitigate these challenges. LLaMAC implements a value distribution encoding similar to that found in the human brain, utilizing internal and external feedback mechanisms to facilitate collaboration and iterative reasoning among its modules. Through evaluations involving system resource allocation and robot grid transportation, we demonstrate the considerable advantages afforded by our proposed approach.

Zhiwei Xu, Hangyu Mao, Nianmin Zhang et al.

In partially observable multi-agent systems, agents typically only have access to local observations. This severely hinders their ability to make precise decisions, particularly during decentralized execution. To alleviate this problem and inspired by image outpainting, we propose State Inference with Diffusion Models (SIDIFF), which uses diffusion models to reconstruct the original global state based solely on local observations. SIDIFF consists of a state generator and a state extractor, which allow agents to choose suitable actions by considering both the reconstructed global state and local observations. In addition, SIDIFF can be effortlessly incorporated into current multi-agent reinforcement learning algorithms to improve their performance. Finally, we evaluated SIDIFF on different experimental platforms, including Multi-Agent Battle City (MABC), a novel and flexible multi-agent reinforcement learning environment we developed. SIDIFF achieved desirable results and outperformed other popular algorithms.

Zhiwei Xu, Dapeng Li, Bin Zhang et al.

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.

Neng Wan, Dapeng Li, Naira Hovakimyan

Sensitivity of linear continuous-time control systems, subject to control and measurement noise, is analyzed by deriving the lower bounds of Bode-like integrals via an information-theoretic approach. Bode integrals of four different sensitivity-like functions are employed to gauge the control trade-offs. When the signals of the control system are stationary Gaussian, these four different Bode-like integrals can be represented as differences between mutual information rates. These mutual information rates and hence the corresponding Bode-like integrals are proven to be bounded below by the unstable poles and zeros of the plant model, if the signals of the control system are wide-sense stationary.

Bin Zhang, Yunpeng Bai, Zhiwei Xu et al.

The application of deep reinforcement learning in multi-agent systems introduces extra challenges. In a scenario with numerous agents, one of the most important concerns currently being addressed is how to develop sufficient collaboration between diverse agents. To address this problem, we consider the form of agent interaction based on neighborhood and propose a multi-agent reinforcement learning (MARL) algorithm based on the actor-critic method, which can adaptively construct the hypergraph structure representing the agent interaction and further implement effective information extraction and representation learning through hypergraph convolution networks, leading to effective cooperation. Based on different hypergraph generation methods, we present two variants: Actor Hypergraph Convolutional Critic Network (HGAC) and Actor Attention Hypergraph Critic Network (ATT-HGAC). Experiments with different settings demonstrate the advantages of our approach over other existing methods.

Zhiwei Xu, Bin Zhang, Dapeng Li et al.

Almost all multi-agent reinforcement learning algorithms without communication follow the principle of centralized training with decentralized execution. During centralized training, agents can be guided by the same signals, such as the global state. During decentralized execution, however, agents lack the shared signal. Inspired by viewpoint invariance and contrastive learning, we propose consensus learning for cooperative multi-agent reinforcement learning in this paper. Although based on local observations, different agents can infer the same consensus in discrete space. During decentralized execution, we feed the inferred consensus as an explicit input to the network of agents, thereby developing their spirit of cooperation. Our proposed method can be extended to various multi-agent reinforcement learning algorithms with small model changes. Moreover, we carry out them on some fully cooperative tasks and get convincing results.

Dapeng Li, Zhiwei Xu, Bin Zhang et al.

Centralized training with decentralized execution (CTDE) is a widely-used learning paradigm that has achieved significant success in complex tasks. However, partial observability issues and the absence of effectively shared signals between agents often limit its effectiveness in fostering cooperation. While communication can address this challenge, it simultaneously reduces the algorithm's practicality. Drawing inspiration from human team cooperative learning, we propose a novel paradigm that facilitates a gradual shift from explicit communication to tacit cooperation. In the initial training stage, we promote cooperation by sharing relevant information among agents and concurrently reconstructing this information using each agent's local trajectory. We then combine the explicitly communicated information with the reconstructed information to obtain mixed information. Throughout the training process, we progressively reduce the proportion of explicitly communicated information, facilitating a seamless transition to fully decentralized execution without communication. Experimental results in various scenarios demonstrate that the performance of our method without communication can approaches or even surpasses that of QMIX and communication-based methods.

Bin Zhang, Lijuan Li, Zhiwei Xu et al.

In multi-agent reinforcement learning (MARL), self-interested agents attempt to establish equilibrium and achieve coordination depending on game structure. However, existing MARL approaches are mostly bound by the simultaneous actions of all agents in the Markov game (MG) framework, and few works consider the formation of equilibrium strategies via asynchronous action coordination. In view of the advantages of Stackelberg equilibrium (SE) over Nash equilibrium, we construct a spatio-temporal sequential decision-making structure derived from the MG and propose an N-level policy model based on a conditional hypernetwork shared by all agents. This approach allows for asymmetric training with symmetric execution, with each agent responding optimally conditioned on the decisions made by superior agents. Agents can learn heterogeneous SE policies while still maintaining parameter sharing, which leads to reduced cost for learning and storage and enhanced scalability as the number of agents increases. Experiments demonstrate that our method effectively converges to the SE policies in repeated matrix game scenarios, and performs admirably in immensely complex settings including cooperative tasks and mixed tasks.

Dapeng Li, Feiyang Pan, Jia He et al.

In high-dimensional time-series analysis, it is essential to have a set of key factors (namely, the style factors) that explain the change of the observed variable. For example, volatility modeling in finance relies on a set of risk factors, and climate change studies in climatology rely on a set of causal factors. The ideal low-dimensional style factors should balance significance (with high explanatory power) and stability (consistent, no significant fluctuations). However, previous supervised and unsupervised feature extraction methods can hardly address the tradeoff. In this paper, we propose Style Miner, a reinforcement learning method to generate style factors. We first formulate the problem as a Constrained Markov Decision Process with explanatory power as the return and stability as the constraint. Then, we design fine-grained immediate rewards and costs and use a Lagrangian heuristic to balance them adaptively. Experiments on real-world financial data sets show that Style Miner outperforms existing learning-based methods by a large margin and achieves a relatively 10% gain in R-squared explanatory power compared to the industry-renowned factors proposed by human experts.

Dapeng Li, Zhiwei Xu, Bin Zhang et al.

Spatial information is essential in various fields. How to explicitly model according to the spatial location of agents is also very important for the multi-agent problem, especially when the number of agents is changing and the scale is enormous. Inspired by the point cloud task in computer vision, we propose a spatial information extraction structure for multi-agent reinforcement learning in this paper. Agents can effectively share the neighborhood and global information through a spatially encoder-decoder structure. Our method follows the centralized training with decentralized execution (CTDE) paradigm. In addition, our structure can be applied to various existing mainstream reinforcement learning algorithms with minor modifications and can deal with the problem with a variable number of agents. The experiments in several multi-agent scenarios show that the existing methods can get convincing results by adding our spatially explicit architecture.

Zhiwei Xu, Bin Zhang, Dapeng Li et al.

Value decomposition methods have gained popularity in the field of cooperative multi-agent reinforcement learning. However, almost all existing methods follow the principle of Individual Global Max (IGM) or its variants, which limits their problem-solving capabilities. To address this, we propose a dual self-awareness value decomposition framework, inspired by the notion of dual self-awareness in psychology, that entirely rejects the IGM premise. Each agent consists of an ego policy for action selection and an alter ego value function to solve the credit assignment problem. The value function factorization can ignore the IGM assumption by utilizing an explicit search procedure. On the basis of the above, we also suggest a novel anti-ego exploration mechanism to avoid the algorithm becoming stuck in a local optimum. As the first fully IGM-free value decomposition method, our proposed framework achieves desirable performance in various cooperative tasks.

Ziqi Han, Ziwei Wan, Hengwei Zhang et al.

Driven by the ultra-high throughput requirements of 6G, wireless communications are migrating to centimeter wave (cmWave) bands to overcome the limitations of current spectral resources. Massive multiple-input multiple-output (MIMO) and orthogonal frequency division multiplexing (OFDM) systems aim to achieve high spectral efficiency in cmWave regimes but are often constrained by the heavy overhead of downlink channel state information (CSI) feedback. This paper proposes a deep learning scheme based on the multi-axis multi-layer perceptron for image processing (MAXIM) architecture for joint semantic CSI feedback and hybrid beamforming in multi-user cmWave MIMO-OFDM systems, which maximizes the downlink sum rate by end-to-end optimization. Specifically, distributed encoders at multiple user equipments (UEs) perform limited CSI feedback, while the decoder at the base station (BS) jointly designs the hybrid beamforming matrices without explicit CSI reconstruction. The uplink transmission is implemented via deep joint source-channel coding (DJSCC) to enhance CSI compression efficiency and noise robustness. Furthermore, considering the high correlation between vertical and horizontal polarization channels in dual-polarized massive MIMO systems, a cross-polarization interaction module is introduced at the UEs to exploit polarization correlations for joint CSI compression. Simulation results demonstrate that the proposed method improves the downlink sum rate under various signal-to-noise ratio (SNR) conditions with a limited number of feedback symbols, validating its robustness and superiority in multi-user dual-polarized cmWave MIMO-OFDM systems.

Junjie Song, Yiwen Liu, Dapeng Li et al.

Text summarization is a crucial task that requires the simultaneous optimization of multiple objectives, including consistency, coherence, relevance, and fluency, which presents considerable challenges. Although large language models (LLMs) have demonstrated remarkable performance, enhanced by reinforcement learning (RL), few studies have focused on optimizing the multi-objective problem of summarization through RL based on LLMs. In this paper, we introduce hypervolume optimization (HVO), a novel optimization strategy that dynamically adjusts the scores between groups during the reward process in RL by using the hypervolume method. This method guides the model's optimization to progressively approximate the pareto front, thereby generating balanced summaries across multiple objectives. Experimental results on several representative summarization datasets demonstrate that our method outperforms group relative policy optimization (GRPO) in overall scores and shows more balanced performance across different dimensions. Moreover, a 7B foundation model enhanced by HVO performs comparably to GPT-4 in the summarization task, while maintaining a shorter generation length. Our code is publicly available at https://github.com/ai4business-LiAuto/HVO.git

Tiezheng Guo, Qingwen Yang, Chen Wang et al.

Large language model (LLM) has achieved outstanding performance on various downstream tasks with its powerful natural language understanding and zero-shot capability, but LLM still suffers from knowledge limitation. Especially in scenarios that require long logical chains or complex reasoning, the hallucination and knowledge limitation of LLM limit its performance in question answering (QA). In this paper, we propose a novel framework KnowledgeNavigator to address these challenges by efficiently and accurately retrieving external knowledge from knowledge graph and using it as a key factor to enhance LLM reasoning. Specifically, KnowledgeNavigator first mines and enhances the potential constraints of the given question to guide the reasoning. Then it retrieves and filters external knowledge that supports answering through iterative reasoning on knowledge graph with the guidance of LLM and the question. Finally, KnowledgeNavigator constructs the structured knowledge into effective prompts that are friendly to LLM to help its reasoning. We evaluate KnowledgeNavigator on multiple public KGQA benchmarks, the experiments show the framework has great effectiveness and generalization, outperforming previous knowledge graph enhanced LLM methods and is comparable to the fully supervised models.

Dapeng Li, Hang Dong, Lu Wang et al.

In recent years, multi-agent reinforcement learning algorithms have made significant advancements in diverse gaming environments, leading to increased interest in the broader application of such techniques. To address the prevalent challenge of partial observability, communication-based algorithms have improved cooperative performance through the sharing of numerical embedding between agents. However, the understanding of the formation of collaborative mechanisms is still very limited, making designing a human-understandable communication mechanism a valuable problem to address. In this paper, we propose a novel multi-agent reinforcement learning algorithm that embeds large language models into agents, endowing them with the ability to generate human-understandable verbal communication. The entire framework has a message module and an action module. The message module is responsible for generating and sending verbal messages to other agents, effectively enhancing information sharing among agents. To further enhance the message module, we employ a teacher model to generate message labels from the global view and update the student model through Supervised Fine-Tuning (SFT). The action module receives messages from other agents and selects actions based on current local observations and received messages. Experiments conducted on the Overcooked game demonstrate our method significantly enhances the learning efficiency and performance of existing methods, while also providing an interpretable tool for humans to understand the process of multi-agent cooperation.

Dapeng Li, Na Lou, Bin Zhang et al.

Parameter sharing, as an important technique in multi-agent systems, can effectively solve the scalability issue in large-scale agent problems. However, the effectiveness of parameter sharing largely depends on the environment setting. When agents have different identities or tasks, naive parameter sharing makes it difficult to generate sufficiently differentiated strategies for agents. Inspired by research pertaining to the brain in biology, we propose a novel parameter sharing method. It maps each type of agent to different regions within a shared network based on their identity, resulting in distinct subnetworks. Therefore, our method can increase the diversity of strategies among different agents without introducing additional training parameters. Through experiments conducted in multiple environments, our method has shown better performance than other parameter sharing methods.

Bin Zhang, Hangyu Mao, Lijuan Li et al.

Asynchronous action coordination presents a pervasive challenge in Multi-Agent Systems (MAS), which can be represented as a Stackelberg game (SG). However, the scalability of existing Multi-Agent Reinforcement Learning (MARL) methods based on SG is severely constrained by network structures or environmental limitations. To address this issue, we propose the Stackelberg Decision Transformer (STEER), a heuristic approach that resolves the difficulties of hierarchical coordination among agents. STEER efficiently manages decision-making processes in both spatial and temporal contexts by incorporating the hierarchical decision structure of SG, the modeling capability of autoregressive sequence models, and the exploratory learning methodology of MARL. Our research contributes to the development of an effective and adaptable asynchronous action coordination method that can be widely applied to various task types and environmental configurations in MAS. Experimental results demonstrate that our method can converge to Stackelberg equilibrium solutions and outperforms other existing methods in complex scenarios.

Zhiwei Xu, Yunpeng Bai, Bin Zhang et al.

Recently, some challenging tasks in multi-agent systems have been solved by some hierarchical reinforcement learning methods. Inspired by the intra-level and inter-level coordination in the human nervous system, we propose a novel value decomposition framework HAVEN based on hierarchical reinforcement learning for fully cooperative multi-agent problems. To address the instability arising from the concurrent optimization of policies between various levels and agents, we introduce the dual coordination mechanism of inter-level and inter-agent strategies by designing reward functions in a two-level hierarchy. HAVEN does not require domain knowledge and pre-training, and can be applied to any value decomposition variant. Our method achieves desirable results on different decentralized partially observable Markov decision process domains and outperforms other popular multi-agent hierarchical reinforcement learning algorithms.

Zhiwei Xu, Dapeng Li, Yunpeng Bai et al.

In the real world, many tasks require multiple agents to cooperate with each other under the condition of local observations. To solve such problems, many multi-agent reinforcement learning methods based on Centralized Training with Decentralized Execution have been proposed. One representative class of work is value decomposition, which decomposes the global joint Q-value $Q_\text{jt}$ into individual Q-values $Q_a$ to guide individuals' behaviors, e.g. VDN (Value-Decomposition Networks) and QMIX. However, these baselines often ignore the randomness in the situation. We propose MMD-MIX, a method that combines distributional reinforcement learning and value decomposition to alleviate the above weaknesses. Besides, to improve data sampling efficiency, we were inspired by REM (Random Ensemble Mixture) which is a robust RL algorithm to explicitly introduce randomness into the MMD-MIX. The experiments demonstrate that MMD-MIX outperforms prior baselines in the StarCraft Multi-Agent Challenge (SMAC) environment.

Junyan Liu, Shuai Li, Dapeng Li

We study the problem of stochastic bandits with adversarial corruptions in the cooperative multi-agent setting, where $V$ agents interact with a common $K$-armed bandit problem, and each pair of agents can communicate with each other to expedite the learning process. In the problem, the rewards are independently sampled from distributions across all agents and rounds, but they may be corrupted by an adversary. Our goal is to minimize both the overall regret and communication cost across all agents. We first show that an additive term of corruption is unavoidable for any algorithm in this problem. Then, we propose a new algorithm that is agnostic to the level of corruption. Our algorithm not only achieves near-optimal regret in the stochastic setting, but also obtains a regret with an additive term of corruption in the corrupted setting, while maintaining efficient communication. The algorithm is also applicable for the single-agent corruption problem, and achieves a high probability regret that removes the multiplicative dependence of $K$ on corruption level. Our result of the single-agent case resolves an open question from Gupta et al. [2019].

Zhiwei Xu, Yunpeng Bai, Dapeng Li et al.

As one of the solutions to the decentralized partially observable Markov decision process (Dec-POMDP) problems, the value decomposition method has achieved significant results recently. However, most value decomposition methods require the fully observable state of the environment during training, but this is not feasible in some scenarios where only incomplete and noisy observations can be obtained. Therefore, we propose a novel value decomposition framework, named State Inference for value DEcomposition (SIDE), which eliminates the need to know the global state by simultaneously seeking solutions to the two problems of optimal control and state inference. SIDE can be extended to any value decomposition method to tackle partially observable problems. By comparing with the performance of different algorithms in StarCraft II micromanagement tasks, we verified that though without accessible states, SIDE can infer the current state that contributes to the reinforcement learning process based on past local observations and even achieve superior results to many baselines in some complex scenarios.

Zhiwei Xu, Bin Zhang, Yunpeng Bai et al.

The collaboration between agents has gradually become an important topic in multi-agent systems. The key is how to efficiently solve the credit assignment problems. This paper introduces MGAN for collaborative multi-agent reinforcement learning, a new algorithm that combines graph convolutional networks and value-decomposition methods. MGAN learns the representation of agents from different perspectives through multiple graph networks, and realizes the proper allocation of attention between all agents. We show the amazing ability of the graph network in representation learning by visualizing the output of the graph network, and therefore improve interpretability for the actions of each agent in the multi-agent system.

Neng Wan, Dapeng Li, Naira Hovakimyan

This paper introduces the $f$-divergence variational inference ($f$-VI) that generalizes variational inference to all $f$-divergences. Initiated from minimizing a crafty surrogate $f$-divergence that shares the statistical consistency with the $f$-divergence, the $f$-VI framework not only unifies a number of existing VI methods, e.g. Kullback-Leibler VI, Rényi's $α$-VI, and $χ$-VI, but offers a standardized toolkit for VI subject to arbitrary divergences from $f$-divergence family. A general $f$-variational bound is derived and provides a sandwich estimate of marginal likelihood (or evidence). The development of the $f$-VI unfolds with a stochastic optimization scheme that utilizes the reparameterization trick, importance weighting and Monte Carlo approximation; a mean-field approximation scheme that generalizes the well-known coordinate ascent variational inference (CAVI) is also proposed for $f$-VI. Empirical examples, including variational autoencoders and Bayesian neural networks, are provided to demonstrate the effectiveness and the wide applicability of $f$-VI.

Neng Wan, Dapeng Li, Naira Hovakimyan

Bode integrals of sensitivity and sensitivity-like functions along with complementary sensitivity and complementary sensitivity-like functions are conventionally used for describing performance limitations of a feedback control system. In this paper, we show that in the case when the disturbance is a wide sense stationary process the (complementary) sensitivity Bode integral and the (complementary) sensitivity-like Bode integral are identical. A lower bound of the continuous-time complementary sensitivity-like Bode integral is also derived and examined with the linearized flight-path angle tracking control problem of an F-16 aircraft.

Mingbo Ma, Dapeng Li, Kai Zhao et al.

This paper describes Oregon State University's submissions to the shared WMT'17 task "multimodal translation task I". In this task, all the sentence pairs are image captions in different languages. The key difference between this task and conventional machine translation is that we have corresponding images as additional information for each sentence pair. In this paper, we introduce a simple but effective system which takes an image shared between different languages, feeding it into the both encoding and decoding side. We report our system's performance for English-French and English-German with Flickr30K (in-domain) and MSCOCO (out-of-domain) datasets. Our system achieves the best performance in TER for English-German for MSCOCO dataset.