Noisy sensing, imperfect control, and environment changes are defining characteristics of many real-world robot tasks. The partially observable Markov decision process (POMDP) …
Markov decision processes (MDPs) are often used to model sequential decision problems involving uncertainty under the assumption of centralized control. However, many large …
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 …
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 …
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 …
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 …
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 …
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 …
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 …