King Fahd University of Petroleum and Minerals

Anas Mohammed Albaghajati

Lahouari Ghouti

Sami El Ferik

Mohammad Tariq Nasir

A reinforcement learning method and apparatus includes storing video frames in a video memory, performing a first preprocessing step of retrieving a sequence of n image frames of the stored video frames, and merging the n image frames in a fading-in fashion by incrementally increasing the intensity of each frame up to the most recent frame having full intensity to obtain a merged frame; and performing a training step of inputting the merged frame to the DQN and training the DQN to learn Q-values for all possible actions from a state represented by the merged frame with only a single forward pass through the network. The learning method and apparatus includes a second preprocessing step of removing the background from the merged frame. The method can be applied to any DQN learning method that uses a convolution neural network as its core value function approximator.

Enhanced deep reinforcement learning deep q-network models

Described herein a robot assisted method of deploying sensors in a geographic region. The method of deploying sensors is posed as a Markovian decision process. The robot assigns each grid cell in a map of the geographic region a reward value based on a surface elevation of the geographic region and a soil hardness factor. Further, the robot determines an action for each grid cell of the plurality of grid cells, wherein the action corresponds to an expected direction of movement of the robot in the grid cell. The robot computes a global path as a concatenation of actions starting from a first grid cell and terminating at a second grid cell. The method monitors the movement of the robot on the computed global path and computes a second path based on a deviation of the robot from the global path.

Growing community of inventors

Dhahran, Saudi Arabia

Anas Mohammed Albaghajati