Sign in
Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement.
Hui Yuan
Kaixuan Huang
Chengzhuo Ni
Minshuo Chen
Mengdi Wang
Published in:
CoRR (2023)
Keyphrases
</>
reinforcement learning
long run
random variables
probability distribution
spatial distribution
estimation accuracy
bandit problems
social networks
significant improvement
diffusion process
reward function
average reward
random field model
inverse reinforcement learning
expected reward