Related papers: POWQMIX: Weighted Value Factorization with Potenti…
In Cooperative Multi-Agent Reinforcement Learning (MARL) and under the setting of Centralized Training with Decentralized Execution (CTDE), agents observe and interact with their environment locally and independently. With local observation…
We explore value decomposition solutions for multi-agent deep reinforcement learning in the popular paradigm of centralized training with decentralized execution(CTDE). As the recognized best solution to CTDE, Weighted QMIX is cutting-edge…
We propose FACtored Multi-Agent Centralised policy gradients (FACMAC), a new method for cooperative multi-agent reinforcement learning in both discrete and continuous action spaces. Like MADDPG, a popular multi-agent actor-critic method,…
Training for multi-agent reinforcement learning(MARL) is a time-consuming process caused by distribution shift of each agent. One drawback is that strategy of each agent in MARL is independent but actually in cooperation. Thus, a vertical…
A practical challenge in reinforcement learning are combinatorial action spaces that make planning computationally demanding. For example, in cooperative multi-agent reinforcement learning, a potentially large number of agents jointly…
Learning a stable and generalizable centralized value function (CVF) is a crucial but challenging task in multi-agent reinforcement learning (MARL), as it has to deal with the issue that the joint action space increases exponentially with…
Centralised training with decentralised execution is an important setting for cooperative deep multi-agent reinforcement learning due to communication constraints during execution and computational tractability in training. In this paper,…
This paper introduces four new algorithms that can be used for tackling multi-agent reinforcement learning (MARL) problems occurring in cooperative settings. All algorithms are based on the Deep Quality-Value (DQV) family of algorithms, a…
Effective coordination and cooperation among agents are crucial for accomplishing individual or shared objectives in multi-agent systems. In many real-world multi-agent systems, agents possess varying abilities and constraints, making it…
By reusing data throughout training, off-policy deep reinforcement learning algorithms offer improved sample efficiency relative to on-policy approaches. For continuous action spaces, the most popular methods for off-policy learning include…
Multi-agent reinforcement learning (MARL) has witnessed significant progress with the development of value function factorization methods. It allows optimizing a joint action-value function through the maximization of factorized per-agent…
Value decomposition (VD) has become one of the most prominent solutions in cooperative multi-agent reinforcement learning. Most existing methods generally explore how to factorize the joint value and minimize the discrepancies between agent…
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…
In the case of the two-person zero-sum stochastic game with a central controller, this paper proposes a best collaborative behavior search and selection algorithm based on reinforcement learning, in response to how to choose the best…
In cooperative multi-agent reinforcement learning (MARL), combining value decomposition with actor-critic enables agents to learn stochastic policies, which are more suitable for the partially observable environment. Given the goal of…
Discrete-action reinforcement learning algorithms often falter in tasks with high-dimensional discrete action spaces due to the vast number of possible actions. A recent advancement leverages value-decomposition, a concept from multi-agent…
In this work we introduce reinforcement learning techniques for solving lexicographic multi-objective problems. These are problems that involve multiple reward signals, and where the goal is to learn a policy that maximises the first reward…
An artificial neural network can be trained by uniformly broadcasting a reward signal to units that implement a REINFORCE learning rule. Though this presents a biologically plausible alternative to backpropagation in training a network, the…
Policy optimization methods with function approximation are widely used in multi-agent reinforcement learning. However, it remains elusive how to design such algorithms with statistical guarantees. Leveraging a multi-agent performance…
Many complex multi-agent systems such as robot swarms control and autonomous vehicle coordination can be modeled as Multi-Agent Reinforcement Learning (MARL) tasks. QMIX, a widely popular MARL algorithm, has been used as a baseline for the…