Devaraj Madhavi
Mapúa Institute of Technology
AutoencoderMachine learningArtificial intelligencePixelTraining (meteorology)Space (commercial competition)Quality (business)Training timeComputer scienceState (computer science)Reinforcement learning
Publications 1
#1Emmanuel Ifeanyi Iroegbu (Mapúa Institute of Technology)
#2Devaraj Madhavi (Mapúa Institute of Technology)
Deep reinforcement learning has been successful in solving common autonomous driving task such as lane keeping by simply using pixel data from front view camera as input. However, raw pixel data contains very high-dimensional observation that affects the learning quality of the agent due to the complexity imposed by a ‘realistic’ urban environment. As a result, we investigate how compressing the raw pixel data from high-dimensional state to low-dimensional latent space using a variational autoen...