DDPG on Pendulum-v1

For a first sweep, I tried DDPG on Pendulum-v1, as only fixed parameters the number of neurons in the two neural networks (400, 300). I discovered later that the parameters were not correctly initialized in the agent, so these are runs of the same agent over and over.

Hugo Vaillaud

Created on September 5|Last edited on September 6

Comment

﻿
Section 1﻿
critic loss
critic loss
Showing first 10 runs
10k20k30k40kStep5101520
actor loss
actor loss
Showing first 10 runs
10k20k30k40kStep1020304050
rewards
rewards
Showing first 10 runs
10k20k30k40kStep-1400-1200-1000-800-600-400-200
Sweep: y7mvr5ee 184
Sweep: y7mvr5ee 20
﻿
﻿
﻿
Sweep: y7mvr5ee84
﻿
﻿

Add a comment