Dynamic Reward Shaping: Training a Robot by Voice.

Ana Cecilia Tenorio-González Eduardo F. Morales Luis Villaseñor Pineda

Published in: IBERAMIA (2010)

Keyphrases

mobile robot
reward shaping
training set
machine learning
path planning
learning algorithm
reinforcement learning
learning process
active learning
dynamic programming
neural network
state space
decision makers
dynamic environments
optimal policy
software agents
decision theoretic