Deep decentralized multi-task multi-agent reinforcement learning under partial observability
S Omidshafiei, J Pazis, C Amato… - … on Machine Learning, 2017 - proceedings.mlr.press
Many real-world tasks involve multiple agents with partial observability and limited
communication. Learning is challenging in these settings due to local viewpoints of agents …
communication. Learning is challenging in these settings due to local viewpoints of agents …
Multi-robot coordination and planning in uncertain and adversarial environments
Abstract Purpose of Review Deploying a team of robots that can carefully coordinate their
actions can make the entire system robust to individual failures. In this report, we review …
actions can make the entire system robust to individual failures. In this report, we review …
Approximate information state for approximate planning and reinforcement learning in partially observed systems
We propose a theoretical framework for approximate planning and learning in partially
observed systems. Our framework is based on the fundamental notion of information state …
observed systems. Our framework is based on the fundamental notion of information state …
Modeling and planning with macro-actions in decentralized POMDPs
Decentralized partially observable Markov decision processes (Dec-POMDPs) are general
models for decentralized multi-agent decision making under uncertainty. However, they …
models for decentralized multi-agent decision making under uncertainty. However, they …
Policy search for multi-robot coordination under uncertainty
We introduce a principled method for multi-robot coordination based on a general model
(termed a MacDec-POMDP) of multi-robot cooperative planning in the presence of …
(termed a MacDec-POMDP) of multi-robot cooperative planning in the presence of …
Deep reinforcement learning for event-driven multi-agent decision processes
The incorporation of macro-actions (temporally extended actions) into multi-agent decision
problems has the potential to address the curse of dimensionality associated with such …
problems has the potential to address the curse of dimensionality associated with such …
Macro-action-based deep multi-agent reinforcement learning
In real-world multi-robot systems, performing high-quality, collaborative behaviors requires
robots to asynchronously reason about high-level action selection at varying time durations …
robots to asynchronously reason about high-level action selection at varying time durations …
Learning to act in decentralized partially observable MDPs
J Dibangoye, O Buffet - International Conference on …, 2018 - proceedings.mlr.press
We address a long-standing open problem of reinforcement learning in decentralized
partially observable Markov decision processes. Previous attempts focussed on different …
partially observable Markov decision processes. Previous attempts focussed on different …
Cooperative multi-agent policy gradient
Reinforcement Learning (RL) for decentralized partially observable Markov decision
processes (Dec-POMDPs) is lagging behind the spectacular breakthroughs of single-agent …
processes (Dec-POMDPs) is lagging behind the spectacular breakthroughs of single-agent …
Learning for multi-robot cooperation in partially observable stochastic environments with macro-actions
This paper presents a data-driven approach for multi-robot coordination in partially-
observable domains based on Decentralized Partially Observable Markov Decision …
observable domains based on Decentralized Partially Observable Markov Decision …