Skip to main content
andrewzhang505
Projects
sample_factory
Reports
Quad-Swarm-RL

Quad-Swarm-RL

Andrew Zhang
Created on July 21|Last edited on July 22
Below are the reward plots with both input and return normalization

200M400M600M800Mglobal_step-100-80-60-40-200
03_baseline_see_3333_20220720_104137_993357
02_baseline_see_2222_20220720_104137_992489
01_baseline_see_1111_20220720_104137_983199
00_baseline_see_0_20220720_104135_336414
200M400M600M800Mglobal_step-6-4-2
03_baseline_see_3333_20220720_104137_993357
02_baseline_see_2222_20220720_104137_992489
01_baseline_see_1111_20220720_104137_983199
00_baseline_see_0_20220720_104135_336414
Run set
4

As a comparison, here are some plots without normalization.

Run set
8


Created with ❤️ on Weights & Biases.

https://wandb.ai/andrewzhang505/sample_factory/reports/Quad-Swarm-RL--VmlldzoyMzU1ODQ1
Made with Weights & Biases. Sign up or log in to create reports like this one.