Random forests and extra trees match a neural network as UDRL behavior functions on CartPole, Acrobot, and Lunar Lander, and provide feature importance explanations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Upside-Down Reinforcement Learning for More Interpretable Optimal Control
Random forests and extra trees match a neural network as UDRL behavior functions on CartPole, Acrobot, and Lunar Lander, and provide feature importance explanations.