Multi-Scale Reward Shaping via an Off-Policy Ensemble.

Anna Harutyunyan Tim Brys Peter Vrancx Ann Nowé

Published in: AAMAS (2015)

Keyphrases

multiscale
reward shaping
reinforcement learning
complex domains
neural network
reinforcement learning algorithms
markov decision problems
training set
state space
learning algorithm
training data
least squares
knowledge acquisition
reward function