Related papers: NQMIX: Non-monotonic Value Function Factorization …
In the field of cooperative multi-agent reinforcement learning (MARL), the standard paradigm is the use of centralised training and decentralised execution where a central critic conditions the policies of the cooperative agents based on a…
Recently, deep multiagent reinforcement learning (MARL) has become a highly active research area as many real-world problems can be inherently viewed as multiagent systems. A particularly interesting and widely applicable class of problems…
Quantum computing has a superior advantage in tackling specific problems, such as integer factorization and Simon's problem. For more general tasks in machine learning, by applying variational quantum circuits, more and more quantum…
Reward decomposition is a critical problem in centralized training with decentralized execution~(CTDE) paradigm for multi-agent reinforcement learning. To take full advantage of global information, which exploits the states from all agents…
This work introduces a novel value decomposition algorithm, termed \textit{Dynamic Deep Factor Graphs} (DDFG). Unlike traditional coordination graphs, DDFG leverages factor graphs to articulate the decomposition of value functions, offering…
This paper concerns imitation learning (IL) (i.e, the problem of learning to mimic expert behaviors from demonstrations) in cooperative multi-agent systems. The learning problem under consideration poses several challenges, characterized by…
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…
In cooperative stochastic games multiple agents work towards learning joint optimal actions in an unknown environment to achieve a common goal. In many real-world applications, however, constraints are often imposed on the actions that can…
Recent works have applied the Proximal Policy Optimization (PPO) to the multi-agent cooperative tasks, such as Independent PPO (IPPO); and vanilla Multi-agent PPO (MAPPO) which has a centralized value function. However, previous literature…
Non-negative matrix factorization (NMF) has previously been shown to be a useful decomposition for multivariate data. We interpret the factorization in a new way and use it to generate missing attributes from test data. We provide a joint…
In real-world multi-robot systems, performing high-quality, collaborative behaviors requires robots to asynchronously reason about high-level action selection at varying time durations. Macro-Action Decentralized Partially Observable Markov…
In this paper, we propose actor-director-critic, a new framework for deep reinforcement learning. Compared with the actor-critic framework, the director role is added, and action classification and action evaluation are applied…
In decentralized multi-agent reinforcement learning, agents learning in isolation can lead to relative over-generalization (RO), where optimal joint actions are undervalued in favor of suboptimal ones. This hinders effective coordination in…
Multimodal sentiment analysis remains a challenging task due to the inherent heterogeneity across modalities. Such heterogeneity often manifests as asynchronous signals, imbalanced information between modalities, and interference from…
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…
We propose using regularization for Multi-Agent Reinforcement Learning rather than learning explicit cooperative structures called {\em Multi-Agent Regularized Q-learning} (MARQ). Many MARL approaches leverage centralized structures in…
We explore value-based multi-agent reinforcement learning (MARL) in the popular paradigm of centralized training with decentralized execution (CTDE). CTDE has an important concept, Individual-Global-Max (IGM) principle, which requires the…
Cooperative multi-agent reinforcement learning (MARL) commonly adopts centralized training with decentralized execution (CTDE), where centralized critics leverage global information to guide decentralized actors. However,…
We formulate an efficient approximation for multi-agent batch reinforcement learning, the approximated multi-agent fitted Q iteration (AMAFQI). We present a detailed derivation of our approach. We propose an iterative policy search and show…
Rapid adaptation in complex control systems remains a central challenge in reinforcement learning. We introduce a framework in which policy and value functions share a low-dimensional coefficient vector - a goal embedding - that captures…