episode_reward = 0
i=0
while i<100:
i+=1
observation, reward, done, info = env.step(env.action_space.sample())
if done:
break
episode_reward += reward
print(f"Step {i}, quality={episode_reward:.3%}")
Following the above code snippets will always return episode_reward equals to 0 for every step.
However, the environment works normally when removing SynchronousSqliteLogger wrapper.
🐛 Bug
Here is the code I ran on Google Colab to create the environment.
and to produce the steps:
Following the above code snippets will always return
episode_reward
equals to0
for every step. However, the environment works normally when removingSynchronousSqliteLogger
wrapper.