Ray tune never done

RLlib
1

Good afternoon.

I have a custom gym Env with with a termination condition like this:

        self.current_step += 1

        if self.current_step >= len(self.df) - 1:
            self.truncated = True
            self.terminated = True

self.df - is a dataset in pd.Dataframe format

When I run ray.tune using the example to run from custom_env.py (from rllib/examples), I get output(PPO):

  episode_len_mean: .nan
  episode_media: {}
  episode_reward_max: .nan
  episode_reward_mean: .nan
  episode_reward_min: .nan
  episodes_this_iter: 0
  episodes_total: 0

However, when I change the condition for completion to this:

        if self.current_step >= 4000 - 1:
            self.truncated = True
            self.terminated = True

Then my error disappears and env still does the action and output is not .nan. What could be the cause of this problem and how to solve it? Dataset has more than 100K rows.