Multimodal Reward Shaping for Efficient Exploration in Reinforcement Learning.

Mingqi Yuan Mon-On Pun Yi Chen Dong Wang Haojun Li

Published in: CoRR (2021)

Keyphrases

reward shaping
reinforcement learning
reinforcement learning algorithms
complex domains
state space
model free
markov decision problems
function approximation
machine learning
multi agent
temporal difference
neural network
dynamic environments
transfer learning
transition model