tensorboard not showing results using ray rllib

Question

I am trainig a reinforcement learning model on google colab using tune and rllib. At first I was able to show the training results useing tensorboard but it is no longer working and I can't seem to find where it comes from, I didn't change anything so I feel a bit lost here.

What it shows (the directory is the right one) :

My current directory :

The training phase:

ray.init(ignore_reinit_error=True)

tune.run("PPO",
         config = {"env" : CustomEnv2,
                  #  "evaluation_interval" : 2,
                  #  "evaluation_num_episodes" : 2,
                   "num_workers" :1},
         num_samples=1,
        #  checkpoint_at_end=True,
         stop={"training_iteration": 10},
         local_dir = './test1')

Plotting results:

%load_ext tensorboard 

%tensorboard --logdir='/content/test1/PPO/PPO_CustomEnv2_024da_00000_0_2022-03-23_09-02-47'

Answer 1

You are using Rllib, right? I actually don't see the tensorboard file (i.e. events.out.tfevents.xxx.xxx) in your path. Maybe you should check if you have this file first.