Design and evaluation of Self-consolidating Concrete (SCC)
Technological innovations in the industry of chemical admixtures for construction materials as concrete, specifically of the superplasticizers, make possible the development at the end of the eighties, of a revolutionary concrete capable of auto ...
Renato Vargas Salazar +1 more
doaj +12 more sources
A survey of multi-agent deep reinforcement learning with communication [PDF]
Communication is an effective mechanism for coordinating the behaviors of multiple agents, broadening their views of the environment, and to support their collaborations. In the field of multi-agent deep reinforcement learning (MADRL), agents can improve
Chang-Xi Zhu, M. Dastani, Shi-Han Wang
semanticscholar +1 more source
Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Exploration [PDF]
We consider the problem of cooperative exploration, where multiple robots need to cooperatively explore an unknown region as fast as possible. Multi-agent reinforcement learning (MARL) has recently become a trending paradigm for solving this challenge ...
Chao Yu +10 more
semanticscholar +1 more source
MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization [PDF]
Experience replay is crucial for off-policy reinforcement learning (RL) methods. By remembering and reusing the experiences from past different policies, experience replay significantly improves the training efficiency and stability of RL algorithms ...
Yong-Sheng Mei +4 more
semanticscholar +1 more source
Warmth and competence in human-agent cooperation [PDF]
Interaction and cooperation with humans are overarching aspirations of artificial intelligence research. Recent studies demonstrate that AI agents trained with deep reinforcement learning are capable of collaborating with humans.
Kevin R. McKee, Xuechunzi Bai, S. Fiske
semanticscholar +1 more source
Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning [PDF]
Centralized Training for Decentralized Execution, where agents are trained offline using centralized information but execute in a decentralized manner online, has gained popularity in the multi-agent reinforcement learning community. In particular, actor-
Xueguang Lyu +3 more
semanticscholar +1 more source
Lifelong Multi-Agent Path Finding in Large-Scale Warehouses [PDF]
Multi-Agent Path Finding (MAPF) is the problem of moving a team of agents to their goal locations without collisions. In this paper, we study the lifelong variant of MAPF, where agents are constantly engaged with new goal locations, such as in large ...
Jiaoyang Li +5 more
semanticscholar +1 more source
The StarCraft Multi-Agent Challenge [PDF]
In the last few years, deep multi-agent reinforcement learning (RL) has become a highly active area of research. A particularly challenging class of problems in this area is partially observable, cooperative, multi-agent learning, in which teams of ...
Mikayel Samvelyan +9 more
semanticscholar +1 more source
Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning [PDF]
Recent studies in multi-agent communicative reinforcement learning (MACRL) have demonstrated that multi-agent coordination can be greatly improved by allowing communication between agents.
Wan-Qi Xue +5 more
semanticscholar +1 more source
Multi-Agent Reinforcement Learning with Temporal Logic Specifications [PDF]
In this paper, we study the problem of learning to satisfy temporal logic specifications with a group of agents in an unknown environment, which may exhibit probabilistic behaviour.
Lewis Hammond +3 more
semanticscholar +1 more source

