Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning.

Zizhao Wang Caroline Wang Xuesu Xiao Yuke Zhu Peter Stone

Published in: AAAI (2024)

Keyphrases

reinforcement learning
state space
high level
state variables
function approximation
data model
robotic control
hidden state
learning algorithm
neural network
hidden markov models
mobile robot
learning process
optimal policy
multi agent
bayesian networks
genetic algorithm