Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Upside Down Reinforcement Learning with Policy Generators

NotificationsYou must be signed in to change notification settings

JacopoD/udrlpg_

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 

Repository files navigation

Screenshot 2024-11-14 at 13 20 55Screenshot 2024-11-14 at 13 21 08

Results

Performance of UDRLPG in three continuous control gym environments and compared to GoGePo (for its similarity) and DDPG (popular RL algorithm for continuous control tasks).

Inverted Pendulum v4

Screenshot 2024-11-14 at 13 22 12

Swimmer v4

Screenshot 2024-11-14 at 13 22 43

Hopper v4

Screenshot 2024-11-14 at 13 23 01
Generator’s ability to produce policies that achieve returns across the entire spectrumScreenshot 2024-11-14 at 13 23 29

Ablation

Weighting strategy and performance-based replay bufferScreenshot 2024-11-14 at 13 26 17

About

Upside Down Reinforcement Learning with Policy Generators

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages


[8]ページ先頭

©2009-2025 Movatter.jp