A study of Q-learning considering negative rewards.

Takayasu Fuchida Kathy Thi Aung Atsushi Sakuragi

Published in: Artif. Life Robotics (2010)

Keyphrases

reinforcement learning
neural network
real time
information retrieval
multi agent
evolutionary algorithm
empirical studies
markov decision processes
genetic algorithm
information systems
search algorithm
optimal policy
credit assignment