MA-Dreamer: Coordination and communication through shared imagination

no code implementations • 10 Apr 2022 • Kenzo Lobos-Tsunekawa, Akshay Srinivasan, Michael Spranger

Multi-agent RL is rendered difficult due to the non-stationary nature of environment perceived by individual agents.

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

no code implementations • 27 Jul 2020 • Kenzo Lobos-Tsunekawa, Tatsuya Harada

Reinforcement Learning (RL), among other learning-based methods, represents powerful tools to solve complex robotic tasks (e. g., actuation, manipulation, navigation, etc.

Reinforcement Learning (RL) Visual Navigation

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

no code implementations • 20 Jun 2017 • Kenzo Lobos-Tsunekawa, David L. Leottau, Javier Ruiz-del-Solar

This paper addresses the design and implementation of complex Reinforcement Learning (RL) behaviors where multi-dimensional action spaces are involved, as well as the need to execute the behaviors in real-time using robotic platforms with limited computational resources and training times.

reinforcement-learning Reinforcement Learning (RL)

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

no code implementations • 20 Jun 2017 • Nicolás Cruz, Kenzo Lobos-Tsunekawa, Javier Ruiz-del-Solar

The main goal of this paper is to analyze the general problem of using Convolutional Neural Networks (CNNs) in robots with limited computational capabilities, and to propose general design guidelines for their use.