Multi-agent deep reinforcement learning: a survey

S Gronauer, K Diepold - Artificial Intelligence Review, 2022 - Springer
The advances in reinforcement learning have recorded sublime success in various domains.
Although the multi-agent domain has been overshadowed by its single-agent counterpart …

Partially observable markov decision processes in robotics: A survey

M Lauri, D Hsu, J Pajarinen - IEEE Transactions on Robotics, 2022 - ieeexplore.ieee.org
Noisy sensing, imperfect control, and environment changes are defining characteristics of
many real-world robot tasks. The partially observable Markov decision process (POMDP) …

Decentralized control of partially observable Markov decision processes

C Amato, G Chowdhary, A Geramifard… - … IEEE Conference on …, 2013 - ieeexplore.ieee.org
Markov decision processes (MDPs) are often used to model sequential decision problems
involving uncertainty under the assumption of centralized control. However, many large …

Multi-agent actor-critic for mixed cooperative-competitive environments

R Lowe, YI Wu, A Tamar, J Harb… - Advances in neural …, 2017 - proceedings.neurips.cc
We explore deep reinforcement learning methods for multi-agent domains. We begin by
analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is …

Graph convolutional reinforcement learning

J Jiang, C Dun, T Huang, Z Lu - arXiv preprint arXiv:1810.09202, 2018 - arxiv.org
Learning to cooperate is crucially important in multi-agent environments. The key is to
understand the mutual interplay between agents. However, multi-agent environments are …

Learning attentional communication for multi-agent cooperation

J Jiang, Z Lu - Advances in neural information processing …, 2018 - proceedings.neurips.cc
Communication could potentially be an effective way for multi-agent cooperation. However,
information sharing among all agents or in predefined communication architectures that …

Graph neural networks for decentralized multi-robot path planning

Q Li, F Gama, A Ribeiro, A Prorok - 2020 IEEE/RSJ international …, 2020 - ieeexplore.ieee.org
Effective communication is key to successful, decentralized, multi-robot path planning. Yet, it
is far from obvious what information is crucial to the task at hand, and how and when it must …

A digital twin-based sim-to-real transfer for deep reinforcement learning-enabled industrial robot grasping

Y Liu, H Xu, D Liu, L Wang - Robotics and Computer-Integrated …, 2022 - Elsevier
Deep reinforcement learning (DRL) has proven to be an effective framework for solving
various complex control problems. In manufacturing, industrial robots can be trained to learn …

Exploration and mapping with groups of robots: Recent trends

A Quattrini Li - Current Robotics Reports, 2020 - Springer
Abstract Purpose of Review Multi-robot exploration—ie, the problem of mapping unknown
features of an environment—is fundamental in many tasks, including search and rescue …

Multi-agent generative adversarial imitation learning

J Song, H Ren, D Sadigh… - Advances in neural …, 2018 - proceedings.neurips.cc
Imitation learning algorithms can be used to learn a policy from expert demonstrations
without access to a reward signal. However, most existing approaches are not applicable in …