Search Results for author:
Found 5 papers, 2 papers with code
Specializing Inter-Agent Communication in Heterogeneous Multi-Agent Reinforcement Learning using Agent Class Information
Inspired by recent advances in agent communication with graph neural networks, this work proposes the representation of multi-agent communication capabilities as a directed labeled heterogeneous agent graph, in which node labels denote agent classes and edge labels, the communication type between two classes of agents.
Multi-agent Reinforcement Learning
Reinforcement Learning (RL)
CAPTION: Correction by Analyses, POS-Tagging and Interpretation of Objects using only Nouns
Recently, Deep Learning (DL) methods have shown an excellent performance in image captioning and visual question answering.
Detecting soccer balls with reduced neural networks: a comparison of multiple architectures under constrained hardware scenarios
We train multiple open implementations of MobileNetV2 and MobileNetV3 models with different underlying architectures, as well as YOLOv3, TinyYOLOv3, YOLOv4 and TinyYOLOv4 in an annotated image data set captured using a mobile robot.
Towards Heterogeneous Multi-Agent Reinforcement Learning with Graph Neural Networks
This work proposes a neural network architecture that learns policies for multiple agent classes in a heterogeneous multi-agent reinforcement setting.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Application and Simulation of Computerized Adaptive Tests Through the Package catsim
This paper presents catsim, the first package written in the Python language specialized in computerized adaptive tests and the logistical models of Item Response Theory.
Applications
