A Genetic Approach to Optimizing the Values of Parameters in Reinforcement Learning for Navigation of a Mobile Robot.
Keiji KameiMasumi IshikawaPublished in: ICONIP (2004)
Keyphrases
- mobile robot
- reinforcement learning
- obstacle avoidance
- parameter values
- indoor environments
- autonomous navigation
- genetic algorithm
- control parameters
- robot control
- unknown environments
- design parameters
- parameter settings
- measured data
- office environment
- learning algorithm
- navigation tasks
- mobile robot navigation
- machine learning
- maximum likelihood
- neural network
- multi agent
- attribute values
- path planning
- continuous variables
- parameter estimation
- dynamic environments
- robotic systems
- probability distribution
- topological map
- outdoor environments
- dynamic programming
- learning process
- initial values
- input variables
- sensitivity analysis