Toward Deep Reinforcement Learning Without a Simulator: An Autonomous Steering Example.
Bar HilleliRan El-YanivPublished in: AAAI (2018)
Keyphrases
- reinforcement learning
- autonomous learning
- real robot
- function approximation
- robotic systems
- state space
- model free
- learning capabilities
- learning algorithm
- robotic control
- multi agent reinforcement learning
- reinforcement learning algorithms
- simulation model
- temporal difference
- multi agent
- mobile robot
- learning process
- cooperative
- stochastic approximation
- autonomous systems
- data sets
- semi autonomous
- case study
- temporal difference learning
- markov decision process
- simulation environment
- test bed
- learning classifier systems
- optimal control