A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions
Deep learning has seen significant growth recently and is now applied to a wide range of
conventional use cases, including graphs. Graph data provides relational information …
conventional use cases, including graphs. Graph data provides relational information …
Human-robot teaming: grand challenges
Abstract Purpose of Review Current real-world interaction between humans and robots is
extremely limited. We present challenges that, if addressed, will enable humans and robots …
extremely limited. We present challenges that, if addressed, will enable humans and robots …
The utility of explainable ai in ad hoc human-machine teaming
R Paleja, M Ghuy… - Advances in neural …, 2021 - proceedings.neurips.cc
Recent advances in machine learning have led to growing interest in Explainable AI (xAI) to
enable humans to gain insight into the decision-making of machine learning models …
enable humans to gain insight into the decision-making of machine learning models …
Heterogeneous multi-robot reinforcement learning
Cooperative multi-robot tasks can benefit from heterogeneity in the robots' physical and
behavioral traits. In spite of this, traditional Multi-Agent Reinforcement Learning (MARL) …
behavioral traits. In spite of this, traditional Multi-Agent Reinforcement Learning (MARL) …
Mixed-initiative multiagent apprenticeship learning for human training of robot teams
Extending recent advances in Learning from Demonstration (LfD) frameworks to multi-robot
settings poses critical challenges such as environment non-stationarity due to partial …
settings poses critical challenges such as environment non-stationarity due to partial …
Multi-UAV planning for cooperative wildfire coverage and tracking with quality-of-service guarantees
In recent years, teams of robot and Unmanned Aerial Vehicles (UAVs) have been
commissioned by researchers to enable accurate, online wildfire coverage and tracking …
commissioned by researchers to enable accurate, online wildfire coverage and tracking …
[PDF][PDF] Learning Efficient Diverse Communication for Cooperative Heterogeneous Teaming.
High-performing teams learn intelligent and efficient communication and coordination
strategies to maximize their joint utility. These teams implicitly understand the different roles …
strategies to maximize their joint utility. These teams implicitly understand the different roles …
Contrastive decision transformers
Decision Transformers (DT) have drawn upon the success of Transformers by abstracting
Reinforcement Learning as a target-return-conditioned, sequence modeling problem. In our …
Reinforcement Learning as a target-return-conditioned, sequence modeling problem. In our …
Self-organized group for cooperative multi-agent reinforcement learning
Centralized training with decentralized execution (CTDE) has achieved great success in
cooperative multi-agent reinforcement learning (MARL) in practical applications. However …
cooperative multi-agent reinforcement learning (MARL) in practical applications. However …
Iterated reasoning with mutual information in cooperative and byzantine decentralized teaming
Information sharing is key in building team cognition and enables coordination and
cooperation. High-performing human teams also benefit from acting strategically with …
cooperation. High-performing human teams also benefit from acting strategically with …