Pretraining & Reinforcement Learning: Sharpening the Axe Before Cutting the Tree.

Saurav Kadavath Samuel Paradis Brian Yao

Published in: CoRR (2021)

Keyphrases

reinforcement learning
tree structure
function approximation
state space
digital images
tree structures
image enhancement
optimal policy
tree construction
gray level
dynamic programming
multi agent
neural network
search algorithm
multiscale
leaf nodes
data sets