However, FACMAClearnsacentralised butfactored critic,which combines per-agent utilities into the joint action-value function via a non-linear monotonic function, as inQMIX, apopular multi-agentQ-learning algorithm. However,unlikeQMIX, there are no inherent constraints on factoring the critic. We thus also employ a nonmonotonic factorisation and empirically demonstrate that its increased representational capacity allows it to solve some tasks that cannot be solved with monolithic, ormonotonically factored critics.

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, our approach uses deep deterministic policy gradients to learn policies. However, FACMAC learns a centralised but factored critic, which combines per-agent utilities into the joint action-value function via a non-linear monotonic function, as in QMIX, a popular multi-agent $Q$-learning algorithm. However, unlike QMIX, there are no inherent constraints on factoring the critic. We thus also employ a nonmonotonic factorisation and empirically demonstrate that its increased representational capacity allows it to solve some tasks that cannot be solved with monolithic, or monotonically factored critics. In addition, FACMAC uses a centralised policy gradient estimator that optimises over the entire joint action space, rather than optimising over each agent's action space separately as in MADDPG. This allows for more coordinated policy changes and fully reaps the benefits of a centralised critic. We evaluate FACMAC on variants of the multi-agent particle environments, a novel multi-agent MuJoCo benchmark, and a challenging set of StarCraft II micromanagement tasks. Empirical results demonstrate FACMAC's superior performance over MADDPG and other baselines on all three domains.

This work presents a conceptual study on the application of Multi-Agent Reinforcement Learning (MARL) for decentralized control of unmanned aerial vehicles to relay a critical data package to a known position. For this purpose, a family of deterministic games is introduced, designed for scaling studies for MARL. A robust baseline policy is proposed, which is based on restricting agent motion envelopes and applying Dijkstra's algorithm. Experimental results show that two off-the-shelf MARL algorithms perform competitively with the baseline for a small number of agents, but scalability issues arise as the number of agents increase.

Neural Information Processing Systems http://nips.cc/

We thank the reviewers for their insightful comments. We will incorporate the feedback and suggestions into the next revision of the paper. A: The messages exchanged between the agents generally convey agent status information (location, health status, etc.) Overtime, communication level gradually decreases as agents move to the right position (step 250,430). We can also design similar experiments to infer the meaning of other types of messages. A: VBC is most beneficial to multi-agent systems that require quick decision making and low communication overhead.

However, unlike QMIX, there are no inherent constraints on factoring the critic. We thus also employ a nonmonotonic factorisation and empirically demonstrate that its increased representational capacity allows it to solve some tasks that cannot be solved with monolithic, or monotonically factored critics.

Unmanned aerial vehicles (UAVs) have been recently utilized in multi-access edge computing (MEC) as edge servers. It is desirable to design UAVs' trajectories and user to UAV assignments to ensure satisfactory service to the users and energy efficient operation simultaneously. The posed optimization problem is challenging to solve because: (i) The formulated problem is non-convex, (ii) Due to the mobility of ground users, their future positions and channel gains are not known in advance, (iii) Local UAVs' observations should be communicated to a central entity that solves the optimization problem. The (semi-) centralized processing leads to communication overhead, communication/processing bottlenecks, lack of flexibility and scalability, and loss of robustness to system failures. To simultaneously address all these limitations, we advocate a fully decentralized setup with no centralized entity. Each UAV obtains its local observation and then communicates with its immediate neighbors only. After sharing information with neighbors, each UAV determines its next position via a locally run deep reinforcement learning (DRL) algorithm. None of the UAVs need to know the global communication graph. Two main components of our proposed solution are (i) Graph attention layers (GAT), and (ii) Experience and parameter sharing proximal policy optimization (EPS-PPO). Our proposed approach eliminates all the limitations of semi-centralized MADRL methods such as MAPPO and MA deep deterministic policy gradient (MADDPG), while guaranteeing a better performance than independent local DRLs such as in IPPO. Numerical results reveal notable performance gains in several different criteria compared to the existing MADDPG algorithm, demonstrating the potential for offering a better performance, while utilizing local communications only.