Behavior coordination for a mobile robot using modular reinforcement learning.
Eiji UchibeMinoru AsadaKoh HosodaPublished in: IROS (1996)
Keyphrases
- mobile robot
- reinforcement learning
- real robot
- autonomous robots
- multi agent reinforcement learning
- multi agent
- path planning
- mobile robot navigation
- multiple robots
- state space
- robot control
- obstacle avoidance
- learning algorithm
- cooperative multi agent systems
- function approximation
- machine learning
- markov decision processes
- mobile robotics
- multi robot
- motion control
- dynamic environments
- simultaneous localization and mapping
- multiagent reinforcement learning
- robot behavior
- distributed agents
- multi agent systems
- multiagent learning
- dynamic programming
- autonomous navigation
- optimal policy
- multiagent systems
- robot navigation
- model free
- indoor environments