Theoretical and Empirical Analysis of Reward Shaping in Reinforcement Learning.

Marek Grzes Daniel Kudenko

Published in: ICMLA (2009)

Keyphrases

reward shaping
reinforcement learning
reinforcement learning algorithms
complex domains
state space
markov decision problems
function approximation
reward function
optimal control
model free
partially observable
multi agent
neural network
markov decision processes
optimal policy
multi agent systems
decision making