Embedded Files
Description:
Description:
On this page 10 trials of the 40cm string and each dynamics model are shown. Each trial shows the performance of the final policy for different reinforcement learning seeds. The green/red trajectories display the ball trajectory while the yellow trajectory shows the trajectory of the cup. The green or red ball trajectories highlight whether the trial was successful (green) or unsuccessful (red). A subset of the videos is shown in on the main page.
On this page 10 trials of the 40cm string and each dynamics model are shown. Each trial shows the performance of the final policy for different reinforcement learning seeds. The green/red trajectories display the ball trajectory while the yellow trajectory shows the trajectory of the cup. The green or red ball trajectories highlight whether the trial was successful (green) or unsuccessful (red). A subset of the videos is shown in on the main page.
Learned Whitebox Model
Learned Whitebox Model
Measured Whitebox Model
Measured Whitebox Model
Long-Term Short Memory (LSTM)
Long-Term Short Memory (LSTM)
Feed Forward Neural Network (FF-NN)
Feed Forward Neural Network (FF-NN)
Page updated
Google Sites
Report abuse