State-wise safe reinforcement learning with pixel observations.

Simon Sinong Zhan Yixuan Wang Qingyuan Wu Ruochen Jiao Chao Huang Qi Zhu

Published in: L4DC (2024)

Keyphrases

reinforcement learning
state space
case study
transition model
machine learning
pairwise
state transitions
data sets
state variables
optimal policy
state abstraction
action space
state transition
pixel values
evaluation function
input image
multi agent
neural network