Search Unity

Search Results

Search Again
Page 1 of 2
  1. Wolf00007
    Post

    SAC freeze when working with demonstration

    @ruoping_unity Thank you for your reply. I still don't really understand why the environment would freeze for so long, even though it is not using...
    Post by: Wolf00007, Aug 3, 2021 in forum: ML-Agents
  2. Wolf00007
    Thread

    SAC freeze when working with demonstration

    Hello, I'm having a problem with SAC training but only when I'm working with behavioral cloning. Normal SAC training takes 25-30 minutes to finish...
    Thread by: Wolf00007, Jul 30, 2021, 2 replies, in forum: ML-Agents
  3. Wolf00007
    Post

    Hyperparameters tuning in ML-Agents

    Are you looking at the graphs only and picking the runs with the highest consistent rewards? Or do you look at the last reward only?
    Post by: Wolf00007, Jul 25, 2021 in forum: ML-Agents
  4. Wolf00007
    Post

    Hyperparameters tuning in ML-Agents

    @mbaske Looks good. I see you're using the values that get generated in TensorBoard. I found something weird when it comes to the timers.json file...
    Post by: Wolf00007, Jul 25, 2021 in forum: ML-Agents
  5. Wolf00007
    Post

    Hyperparameters tuning in ML-Agents

    @mbaske Sounds cool, please let me know in this thread if you manage to finish updating your project :)
    Post by: Wolf00007, Jul 24, 2021 in forum: ML-Agents
  6. Wolf00007
    Thread

    PushBlock example learning starting with very high rewards

    Hello, I have been experimenting with the PushBlock example and different configuration files for it. The learning however looks a bit weird,...
    Thread by: Wolf00007, Jul 24, 2021, 0 replies, in forum: ML-Agents
  7. Wolf00007
    Post

    Hyperparameters tuning in ML-Agents

    @mbaske When you were running your hyperparameter tuner, was the whole process taking a long time? I mean, if I were to test many different...
    Post by: Wolf00007, Jul 23, 2021 in forum: ML-Agents
  8. Wolf00007
    Post

    Hyperparameters tuning in ML-Agents

    So essentially, if I prepare some configs and I run the learning process through an executable (I can then launch all processes one by one), I...
    Post by: Wolf00007, Jul 19, 2021 in forum: ML-Agents
  9. Wolf00007
    Thread

    Hyperparameters tuning in ML-Agents

    Hi there, Is there a good method to tune the hyperparameters using ML-Agents. I know the docs suggest some of the values and I can just try out...
    Thread by: Wolf00007, Jul 18, 2021, 13 replies, in forum: ML-Agents
  10. Wolf00007
    Thread

    Using SAC and Behavioral Cloning together

    Hello! I wanted to do some experiments with the SAC algorithm and Behavioral Cloning, however, the official docs only mention PPO when it comes...
    Thread by: Wolf00007, Jul 15, 2021, 2 replies, in forum: ML-Agents
  11. Wolf00007
    Post

    WallJump example giving bad results when using PPO only

    Hi there! Do you have any news on this matter? :)
    Post by: Wolf00007, Jun 11, 2021 in forum: ML-Agents
  12. Wolf00007
    Post

    WallJump example giving bad results when using PPO only

    Hi @andrewcoh_unity Thank you so much for your response! I have noticed two other things: 1. When I tried to use the models made by Unity,...
    Post by: Wolf00007, Jun 8, 2021 in forum: ML-Agents
  13. Wolf00007
    Thread

    WallJump example giving bad results when using PPO only

    Hello! So I have been following the article below to learn more about this WallJump example...
    Thread by: Wolf00007, Jun 6, 2021, 3 replies, in forum: ML-Agents
  14. Wolf00007
    Thread

    Karting Microgame ML-Agents - karts going the wrong way

    Hello, I have a problem with learning my agents in the Karting Microgame. They pretty much have no problem with going through a flat track, left...
    Thread by: Wolf00007, May 13, 2021, 1 replies, in forum: ML-Agents
  15. Wolf00007
    Post

    Resolved Using imitation learning in Karting Microgame

    I think I found the issue. Agents do not have "idle" as an action - they either go forward or brake/go backwards. This is why in Heuristic...
    Post by: Wolf00007, May 7, 2021 in forum: ML-Agents
  16. Wolf00007
    Post

    Resolved Using imitation learning in Karting Microgame

    Okay I changed the following: void InterpretDiscreteActions(float[] actions) { m_Steering = actions[0]; m_Brake =...
    Post by: Wolf00007, May 6, 2021 in forum: ML-Agents
  17. Wolf00007
    Post

    Resolved Using imitation learning in Karting Microgame

    Now the car goes forward by itself, still steering right (@Edit - left, sorry) o_O I noticed that currently I am using both Agent and IInput...
    Post by: Wolf00007, May 6, 2021 in forum: ML-Agents
  18. Wolf00007
    Post

    Resolved Using imitation learning in Karting Microgame

    That's okay, thank you for the quick responses :) I have tried the mapping like above and the errors are gone but once again, the agent is still...
    Post by: Wolf00007, May 5, 2021 in forum: ML-Agents
  19. Wolf00007
    Post

    Resolved Using imitation learning in Karting Microgame

    I already have two branches with 3 actions per branch [ATTACH] Again, as this is a microgame, this was already prepared like this so I'm not...
    Post by: Wolf00007, May 5, 2021 in forum: ML-Agents
  20. Wolf00007
    Post

    Resolved Using imitation learning in Karting Microgame

    I have just did that and the error was gone but after hitting Play, I got hundreds of errors like this: [ATTACH]
    Post by: Wolf00007, May 5, 2021 in forum: ML-Agents
Showing results 1 to 20 of 24 Next >
Search Again
Page 1 of 2