Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning.

Takato Okudo Seiji Yamada

Published in: CoRR (2021)

Keyphrases

reinforcement learning
reward shaping
reinforcement learning algorithms
neural network
learning algorithm
multi agent
computational complexity
dynamic programming
knowledge base
state space
case based reasoning
knowledge acquisition
optimal policy
optimal control
transition model