An evolutionary multi-objective network search with teacher-student transfer learning finds a convolutional policy for simulated autonomous driving that scores 4% higher reward than a manual baseline.
Hyperparameter optimiza- tion for ˆA driving strategies based on ˆA reinforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Robust Evolutionary Multi-Objective Network Architecture Search for Reinforcement Learning (EMNAS-RL)
An evolutionary multi-objective network search with teacher-student transfer learning finds a convolutional policy for simulated autonomous driving that scores 4% higher reward than a manual baseline.