Effectiveness of Reward Functions for Deep Reinforcement Learning in Chick-Feeding System.

Masato Kijima Katsuhide Fujita

Published in: IIAI-AAI-Winter (2023)

Keyphrases

reinforcement learning
reward function
markov decision processes
policy search
reinforcement learning algorithms
optimal policy

markov decision process
state space
multi agent
function approximation
transition probabilities
inverse reinforcement learning

simple examples
learning agent
maximum entropy
multiple agents
partially observable
machine learning

state variables
state action
continuous state
random walk
image segmentation