Regression Report: wandb

[['?we=costa-huang&wpn=trl&ceik=tracker_project_name&cen=log_with&metrics=env/reward_mean', 'wandb?tag=calculator_few_shots_env_no_training&tag=pr-429&cl=baseline (no training at all)', 'wandb?tag=calculator_few_shots_env&tag=pr-429&cl=calculator_env (various improvement)']]

Costa

Created on June 15|Last edited on June 15

Comment

﻿
﻿
env/reward_mean trl
env/reward_mean trl
100200300Steps00.20.40.60.81Episodic Return
env/reward_mean trl
env/reward_mean trl
10203040Time (minutes)00.20.40.60.81Episodic Return
baseline (no training at all)10
calculator_env (various improvement)10
﻿
﻿

Add a comment