robo-gym - An Open Source Toolkit for Distributed Deep Reinforcement Learning on Real and Simulated Robots.
Matteo LucchiFriedemann ZindlerStephan Mühlbacher-KarrerHorst PichlerPublished in: IROS (2020)
Keyphrases
- real robot
- open source
- reinforcement learning
- mobile robot
- multi agent
- cooperative
- real environment
- multi robot
- distributed systems
- real life
- robotic control
- distributed environment
- robot teams
- multiple robots
- real world
- function approximation
- robot control
- human robot interaction
- fault tolerant
- distributed data
- open source software
- neural network
- transfer learning
- dynamic environments
- source code
- learning process
- communication cost
- humanoid robot
- computer networks
- markov decision processes
- map reduce
- reinforcement learning methods
- multi robot coordination