Add to ORKGWe consider the problem of multi-agent navigation and collision avoidance when observations are limited to the local neighborhood of each agent. We propose InforMARL, a novel architecture for multi-agent reinforcement learning (MARL) which uses local information intelligently to compute paths for all the agents in a decentralized manner. Specifically, InforMARL aggregates information about the local neighborhood of agents for both the actor and the critic using a graph neural network and can be used in conjunction with any standard MARL algorithm. We show that (1) in training, InforMARL has better sample efficiency and performance than baseline approaches, despite using less information, and (2) in testing, it scales well to environments wi...
Efficient exploration is important for reinforcement learners to achieve high rewards. In multi-agen...
Traditional centralized multi-agent reinforcement learning (MARL) algorithms are sometimes unpractic...
Multi-agent reinforcement learning (MARL) enables us to create adaptive agents in challenging enviro...
The development of autonomous agents which can interact with other agents to accomplish a given task...
Cooperative multi-agent reinforcement learning (MARL) has achieved significant results, most notably...
We tackle the problem of cooperative visual exploration where multiple agents need to jointly explor...
Multi-robot navigation is a challenging task in which multiple robots must be coordinated simultaneo...
Many recent breakthroughs in multi-agent reinforcement learning (MARL) require the use of deep neura...
The multi-robot adaptive sampling problem aims at finding trajectories for a team of robots to effic...
Multi-agent reinforcement learning for incomplete information environments has attracted extensive a...
Despite significant advancements in the field of multi-agent navigation, agents still lack the sophi...
With great success in Reinforcement Learning’s application to a suite of single-agent environments, ...
Achieving distributed reinforcement learning (RL) for large-scale cooperative multi-agent systems (M...
We study multi-agent reinforcement learning (MARL) with centralized training and decentralized execu...
Reinforcement learning is the area of machine learning concerned with learning which actions to exec...
Efficient exploration is important for reinforcement learners to achieve high rewards. In multi-agen...
Traditional centralized multi-agent reinforcement learning (MARL) algorithms are sometimes unpractic...
Multi-agent reinforcement learning (MARL) enables us to create adaptive agents in challenging enviro...
The development of autonomous agents which can interact with other agents to accomplish a given task...
Cooperative multi-agent reinforcement learning (MARL) has achieved significant results, most notably...
We tackle the problem of cooperative visual exploration where multiple agents need to jointly explor...
Multi-robot navigation is a challenging task in which multiple robots must be coordinated simultaneo...
Many recent breakthroughs in multi-agent reinforcement learning (MARL) require the use of deep neura...
The multi-robot adaptive sampling problem aims at finding trajectories for a team of robots to effic...
Multi-agent reinforcement learning for incomplete information environments has attracted extensive a...
Despite significant advancements in the field of multi-agent navigation, agents still lack the sophi...
With great success in Reinforcement Learning’s application to a suite of single-agent environments, ...
Achieving distributed reinforcement learning (RL) for large-scale cooperative multi-agent systems (M...
We study multi-agent reinforcement learning (MARL) with centralized training and decentralized execu...
Reinforcement learning is the area of machine learning concerned with learning which actions to exec...
Efficient exploration is important for reinforcement learners to achieve high rewards. In multi-agen...
Traditional centralized multi-agent reinforcement learning (MARL) algorithms are sometimes unpractic...
Multi-agent reinforcement learning (MARL) enables us to create adaptive agents in challenging enviro...