Gradient shaping for multi-constraint safe reinforcement learning.

Yihang Yao Zuxin Liu Zhepeng Cen Peide Huang Tingnan Zhang Wenhao Yu Ding Zhao

Published in: L4DC (2024)

Keyphrases

reinforcement learning
reward shaping
supervised learning
state space
machine learning
multi agent
edge detection
transfer learning
markov decision processes
action selection
linear constraints
policy search
dynamic programming
learning process
gradient method
reinforcement learning methods
neural network