I am training a RL agent whose state is composed of two numbers, ranging between 4 ~ 16 and 0 ~ 360. The action is continuous and between 0~90. In real life, the states can be any I am training a TD3 agent using the stable baselines library. In real life, the state may be any pair of numbers in the aforementioned range. Hence, I am generating random numbers for training. Leading to different data at each episode. I have realized that the trained agent is predicting actions just in the boundaries of the action range. Could this issue be caused by using different data for the different episodes of the training?.


In the real application of my algorithm the pair of numbers will be arbitrary, given that they are in the corresponding range. By random numbers for training I mean that I am generating pairs of numbers using uniform distributions between the given boundaries. And using them to train the system. The reward is a function of these numbers, however it does not have an analytic expression.

  • 1
    $\begingroup$ Can you describe in more detail what you mean with training it on random numbers? Do you mean that the target is non stationary (chances each episode)? $\endgroup$
    – hal9000
    Jan 26, 2022 at 11:51
  • $\begingroup$ This could be a problem related to your implementation So, it might also be a good idea to provide the link (not the code) to the source code for people that would like to look at it, although programming questions (so debugging programming issues) are off-topic here. $\endgroup$
    – nbro
    Jan 31, 2022 at 12:19


You must log in to answer this question.