Efficient Deep Reinforcement Learning Requires Regulating Overfitting.

Qiyang Li Aviral Kumar Ilya Kostrikov Sergey Levine

Published in: CoRR (2023)

Keyphrases

reinforcement learning
neural network
machine learning
genetic algorithm
learning algorithm
learning process
temporal difference
data mining
expert systems
computationally efficient
cost effective
transfer learning
computationally expensive