- Why is a replay buffer used in a DQN?
- Why do we use target networks?
- Why do we stack four frames into one state? Will one frame alone suffice to represent one state?
- Why is the Huber loss sometimes preferred over L2 loss?
- We converted the RGB input image into grayscale. Can we instead use the RGB image as input to the network? What are the pros and cons of using RGB images instead of grayscale?
Germany
Slovakia
Canada
Brazil
Singapore
Hungary
Philippines
Mexico
Thailand
Ukraine
Luxembourg
Estonia
Lithuania
Norway
Chile
United States
Great Britain
India
Spain
South Korea
Ecuador
Colombia
Taiwan
Switzerland
Indonesia
Cyprus
Denmark
Finland
Poland
Malta
Czechia
New Zealand
Austria
Turkey
France
Sweden
Italy
Egypt
Belgium
Portugal
Slovenia
Ireland
Romania
Greece
Argentina
Malaysia
South Africa
Netherlands
Bulgaria
Latvia
Australia
Japan
Russia