Reward-penalty reinforcement learning scheme for planning and reactive behaviour.

Aluizio F. R. Araújo Arthur P. S. Braga

Published in: SMC (1998)

Keyphrases

learning scheme
reinforcement learning
reactive agents
learning algorithm
reactive planning
reward function
heuristic search
agent receives
planning problems
objective function
state space
agent architecture
domain knowledge
planning domains
internal state
reward shaping