相关论文: Beyond Monotonicity: Revisiting Factorization Prin…

Centralized training is widely utilized in the field of multi-agent reinforcement learning (MARL) to assure the stability of training process. Once a joint policy is obtained, it is critical to design a value function factorization method…

Value function decomposition is becoming a popular rule of thumb for scaling up multi-agent reinforcement learning (MARL) in cooperative games. For such a decomposition rule to hold, the assumption of the individual-global max (IGM)…

Cooperative multi-agent reinforcement learning (MARL) commonly adopts centralized training with decentralized execution, where value-factorization methods enforce the individual-global-maximum (IGM) principle so that decentralized greedy…

Many advances in cooperative multi-agent reinforcement learning (MARL) are based on two common design principles: value decomposition and parameter sharing. A typical MARL algorithm of this fashion decomposes a centralized Q-function into…

Multi-Agent Reinforcement Learning (MARL) is useful in many problems that require the cooperation and coordination of multiple agents. Learning optimal policies using reinforcement learning in a multi-agent setting can be very difficult as…

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…

Non-stationarity is a fundamental challenge in multi-agent reinforcement learning (MARL), where agents update their behaviour as they learn. Many theoretical advances in MARL avoid the challenge of non-stationarity by coordinating the…

Value function decomposition methods for cooperative multi-agent reinforcement learning compose joint values from individual per-agent utilities, and train them using a joint objective. To ensure that the action selection process between…

We propose a novel framework for value function factorization in multi-agent deep reinforcement learning (MARL) using graph neural networks (GNNs). In particular, we consider the team of agents as the set of nodes of a complete directed…

Real-world cooperation often requires intensive coordination among agents simultaneously. This task has been extensively studied within the framework of cooperative multi-agent reinforcement learning (MARL), and value decomposition methods…

Value function factorization has achieved great success in multi-agent reinforcement learning by optimizing joint action-value functions through the maximization of factorized per-agent utilities. To ensure Individual-Global-Maximum…

We study multi-agent reinforcement learning (MARL) in infinite-horizon discounted zero-sum Markov games. We focus on the practical but challenging setting of decentralized MARL, where agents make decisions without coordination by a…

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…

Value decomposition is a core approach for cooperative multi-agent reinforcement learning (MARL). However, existing methods still rely on a single optimal action and struggle to adapt when the underlying value function shifts during…

Cooperative multi-agent reinforcement learning (MARL) faces significant scalability issues due to state and action spaces that are exponentially large in the number of agents. As environments grow in size, effective credit assignment…

Value factorization is a popular and promising approach to scaling up multi-agent reinforcement learning in cooperative settings, which balances the learning scalability and the representational capacity of value functions. However, the…

In many real-world tasks, multiple agents must learn to coordinate with each other given their private observations and limited communication ability. Deep multiagent reinforcement learning (Deep-MARL) algorithms have shown superior…

In many real-world settings, a team of agents must coordinate their behaviour while acting in a decentralised way. At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting,…

Decentralized learning has shown great promise for cooperative multi-agent reinforcement learning (MARL). However, non-stationarity remains a significant challenge in fully decentralized learning. In the paper, we tackle the…

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…