Toward Robots' Behavioral Transparency of Temporal Difference Reinforcement Learning With a Human Teacher.
Marco MatareseAlessandra SciuttiFrancesco ReaSilvia RossiPublished in: IEEE Trans. Hum. Mach. Syst. (2021)
Keyphrases
- temporal difference
- human teacher
- reinforcement learning
- imitation learning
- function approximation
- td learning
- learning process
- reinforcement learning algorithms
- model free
- temporal difference learning
- state space
- human subjects
- learning mechanism
- policy evaluation
- action selection
- monte carlo
- reinforcement learning methods
- evaluation function
- function approximators
- step size
- policy iteration
- optimal control
- actor critic
- learning algorithm
- humanoid robot
- markov decision processes
- multi agent
- machine learning
- control problems
- transfer learning
- optimal policy
- supervised learning
- temporal difference methods
- partially observable
- markov decision process
- robotic systems
- dynamic programming
- active learning