Login / Signup
Diverse randomized value functions: A provably pessimistic approach for offline reinforcement learning.
Xudong Yu
Chenjia Bai
Hongyi Guo
Changhong Wang
Zhen Wang
Published in:
Inf. Sci. (2024)
Keyphrases
</>
reinforcement learning
wide variety
function approximation
reinforcement learning algorithms
real time
machine learning
markov decision processes
neural network
learning algorithm
artificial intelligence
basis functions
learning classifier systems
model free
robot control