Login / Signup
A Reward Function Using Image Processing for a Deep Reinforcement Learning Approach Applied to the Sonic the Hedgehog Game.
Felipe Rafael de Souza
Thiago Silva Miranda
Heder Soares Bernardino
Published in:
BRACIS (2) (2022)
Keyphrases
</>
reinforcement learning
reward function
image processing
state space
reinforcement learning algorithms
markov decision processes
optimal policy
transition model
inverse reinforcement learning
initially unknown
hierarchical reinforcement learning
social networks
maximum entropy
partially observable
policy search