CrossNorm: Normalization for Off-Policy TD Reinforcement Learning

By Aditya Bhatt, Max Argus, Artemij Amiranashvili, Thomas Brox. 2019

32 citations recorded by the source corpus.

Subfields: Reinforcement Learning, Optimization & Training

Citations in the corpus

• Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog (2019, neutral): “Normalized feature representations have been proposed as an alternative approach [4].”
• Automated Machine Learning: Methods, Systems, Challenges (2019, unknown): “As mentioned above, in order to facilitate fast training with modern machine learning algorithms, we developed an OpenGL-based simulator “gymduckietown” [7].”
• Normalization Techniques in Training DNNs: Methodology, Analysis and Application (2020, unknown): “Another observation is that normalization is not very common in deep reinforcement learning (DRL) [65].”