Learning the Inverse Model of the Dynamics of a Robot Leg by Auto-imitation.
Karl-Theodor KalveramAndré SeyfarthPublished in: AMS (2007)
Keyphrases
- high level
- reinforcement learning
- mathematical model
- prior knowledge
- minority game
- skill learning
- probabilistic model
- learning algorithm
- learning process
- learning models
- path planning
- imitation learning
- recurrent networks
- learned models
- robot navigation
- dynamic model
- experimental data
- computational model
- probability distribution
- mobile robot
- bayesian networks