Overview of Deep Reinforcement Learning Methods - presented by Prof. Steven L. Brunton

Overview of Deep Reinforcement Learning Methods

Prof. Steven L. Brunton

Prof. Steven L. Brunton
Slide at 16:13
LETTER dok 10.1038/nature14236 Human-level control through deep reinforcement learning Graves' Volodymyr Mnih'* Koray Andreas Kavukcuoglu's K. Fidjeland David Georg Ostrovski Silver Andrei Stig Petersen1, A. Rusu1, Hassabis Joel Charles Veness', Beattle', Marc Amir G. Bellemare1. Sadik' loannis Alex Antonoglou Martin Helen King'. Riedmiller Dharshan Kumaran'. Daan Wierstra', Shane Legg & Demis Convolution Fully connected Fully connected Convolution
1
References
  • 1.
    V. Mnih et al. (2015) Human-level control through deep reinforcement learning. Nature
Share slide
Summary (AI generated)

The architecture consists of convolutional layers and fully connected layers, which enable the conversion of pixel space to joystick signals. Essentially, it is a deep Q learning demonstration that utilizes convolutional Q-learning. Additionally, there is a list of video games presented. The games above the line indicate that the deep Q learning program is better than or equal to human performance, while the games below the line indicate that it is still not as proficient as humans.