Picture for Kenzo Lobos-Tsunekawa

Kenzo Lobos-Tsunekawa

MA-Dreamer: Coordination and communication through shared imagination

Add code
Apr 10, 2022
Figure 1 for MA-Dreamer: Coordination and communication through shared imagination
Figure 2 for MA-Dreamer: Coordination and communication through shared imagination
Figure 3 for MA-Dreamer: Coordination and communication through shared imagination
Figure 4 for MA-Dreamer: Coordination and communication through shared imagination
Viaarxiv icon

Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation

Add code
Jul 27, 2020
Figure 1 for Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation
Figure 2 for Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation
Figure 3 for Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation
Figure 4 for Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation
Viaarxiv icon

Using Convolutional Neural Networks in Robots with Limited Computational Resources: Detecting NAO Robots while Playing Soccer

Add code
Jun 20, 2017
Figure 1 for Using Convolutional Neural Networks in Robots with Limited Computational Resources: Detecting NAO Robots while Playing Soccer
Figure 2 for Using Convolutional Neural Networks in Robots with Limited Computational Resources: Detecting NAO Robots while Playing Soccer
Figure 3 for Using Convolutional Neural Networks in Robots with Limited Computational Resources: Detecting NAO Robots while Playing Soccer
Figure 4 for Using Convolutional Neural Networks in Robots with Limited Computational Resources: Detecting NAO Robots while Playing Soccer
Viaarxiv icon

Toward Real-Time Decentralized Reinforcement Learning using Finite Support Basis Functions

Add code
Jun 20, 2017
Figure 1 for Toward Real-Time Decentralized Reinforcement Learning using Finite Support Basis Functions
Figure 2 for Toward Real-Time Decentralized Reinforcement Learning using Finite Support Basis Functions
Figure 3 for Toward Real-Time Decentralized Reinforcement Learning using Finite Support Basis Functions
Figure 4 for Toward Real-Time Decentralized Reinforcement Learning using Finite Support Basis Functions
Viaarxiv icon