CleanRL PPG vs PPO results

Tracked runs for CleanRL implementation of Phasic Policy Gradient and comparision to PPO.

Created on May 25|Last edited on May 25

Comment

﻿
Results
Environment - "bigfish"﻿
Bigfish Videos
This run didn't log media for key "videos", step 45074, index 0. Docs →
This run didn't log media for key "videos", step 43880, index 0. Docs →
This run didn't log media for key "videos", step 42212, index 0. Docs →
This run didn't log media for key "videos", step 43792, index 0. Docs →
This run didn't log media for key "videos", step 56222, index 0. Docs →
This run didn't log media for key "videos", step 55028, index 0. Docs →
Step
charts/episodic_return
charts/episodic_return
5M10M15M20Mglobal_step010203040
Run set4237
﻿
Environment - "starpilot"﻿
Run set4237
﻿
Environment - "bossfight"﻿
Run set4237
﻿
﻿
﻿

Add a comment