Search Unity

Search Results

Search Again
Page 1 of 8
  1. vincentpierre
    Post

    SAC agent just stops moving randomly

    Entropy is supposed to eventually go down when using PPO or SAC as the algorithm gains more confidence. SAC is much more useful in stationary...
    Post by: vincentpierre, Sep 21, 2021 in forum: ML-Agents
  2. vincentpierre
    Post

    SAC agent just stops moving randomly

    Is there something specific happening in this part of the track? Are the observations all right around that spot or do they take values unseen so...
    Post by: vincentpierre, Sep 8, 2021 in forum: ML-Agents
  3. vincentpierre
    Post

    SAC agent just stops moving randomly

    Strange that SAC would send a constant action for not moving. It could be because the entropy target is too low. Does moving yields some rewards...
    Post by: vincentpierre, Aug 11, 2021 in forum: ML-Agents
  4. vincentpierre
    Post

    SAC agent just stops moving randomly

    Hi, SAC will "stop" very often because it needs to update the policy. SAC is an off-policy algorithm, meaning that it can use a lot more data than...
    Post by: vincentpierre, Aug 10, 2021 in forum: ML-Agents
  5. vincentpierre
    Post

    Max Step in tensorboard doesnt match Max Step of agent

    Ah! Sorry about that. I believe it is because the steps of the agent are counted in FixedUpdates and not in number of decisions. On the other...
    Post by: vincentpierre, Aug 10, 2021 in forum: ML-Agents
  6. vincentpierre
    Post

    Is it possible to rewrite the algorithm of MLAgents?

    I fail to see the difference between the two options. In any case it seems you want to write a learning algorithm in C#. If that is what you want...
    Post by: vincentpierre, Aug 9, 2021 in forum: ML-Agents
  7. vincentpierre
    Post

    Max Step in tensorboard doesnt match Max Step of agent

    Max step on the agent...
    Post by: vincentpierre, Aug 9, 2021 in forum: ML-Agents
  8. vincentpierre
    Post

    trained file (onnx) vs live pyhton

    It is very hard to diagnose what might be wrong from the provided information. It could be that there are some issues with the inference that...
    Post by: vincentpierre, Aug 9, 2021 in forum: ML-Agents
  9. vincentpierre
    Post

    Running Karting Tutorial Model without ML-Agents package

    > ML-Agents package is not compatible with all platforms Which platforms are not supported? ML-Agents should run on all platforms Barracuda...
    Post by: vincentpierre, Aug 9, 2021 in forum: ML-Agents
  10. vincentpierre
    Post

    Compile Errors 2020.3, 2021.1

    I tried to use Unity version 2020.3.12f1 with the latest release of ML-Agents to open the example environments and I did not see any compilation...
    Post by: vincentpierre, Aug 9, 2021 in forum: ML-Agents
  11. vincentpierre
    Post

    unity preview packages - plans for verification?

    Hi, We currently do not have a date for a verified release. Since ML-Agents relies on Python code for training, it will take a long time to get...
    Post by: vincentpierre, Aug 5, 2021 in forum: ML-Agents
  12. vincentpierre
    Post

    Training for longer period of time shows worse results

    Yes, you need to make sure there will not be a case where the resetting is not behaving like you expect. You also need to make sure the scene...
    Post by: vincentpierre, Aug 5, 2021 in forum: ML-Agents
  13. vincentpierre
    Post

    Tensorboard metrics data missing

    It is possible that if the summary frequency is too high, there are summaries that do not see an episode ending at all. Increasing the time...
    Post by: vincentpierre, Aug 4, 2021 in forum: ML-Agents
  14. vincentpierre
    Post

    Training for longer period of time shows worse results

    Does you environment reset properly when the agents terminate? It could be that the environment randomly enters a weird state that prevents the...
    Post by: vincentpierre, Aug 4, 2021 in forum: ML-Agents
  15. vincentpierre
    Post

    Question Why ML-Agents don't use all my system resources?

    Maxing out ml-agents CPU usage is hard because there exist several bottlenecks that are not CPU related, like exchanging data between Unity and...
    Post by: vincentpierre, Aug 4, 2021 in forum: ML-Agents
  16. vincentpierre
    Post

    how to inference trained models.

    If you want to do inference with Python not with the latest model, we do not have an official way of supporting this. But you should be able to...
    Post by: vincentpierre, Aug 4, 2021 in forum: ML-Agents
  17. vincentpierre
    Post

    how to inference trained models.

    Hi, Resume will load the latest model the resulted from training. We currently do not support using another model for loading. Maybe you could...
    Post by: vincentpierre, Aug 3, 2021 in forum: ML-Agents
  18. vincentpierre
    Post

    Resolved Can't load trained model for inference

    v1.0.6 C# mlagents only supports up to Python mlagents 0.20.0 according to this page :...
    Post by: vincentpierre, Jun 29, 2021 in forum: ML-Agents
  19. vincentpierre
    Post

    Resolved Can't load trained model for inference

    Ok, but what is the version of ML-Agents on C# ? Go to package manager and look for ML-Agents, it should show the version you are on. Please also...
    Post by: vincentpierre, Jun 23, 2021 in forum: ML-Agents
  20. vincentpierre
    Post

    Resolved Can't load trained model for inference

    Your barracuda version is 1.0.4 which is very old. I think you might be using a version of the ML-Agents package that is too ancient compared to...
    Post by: vincentpierre, Jun 16, 2021 in forum: ML-Agents
Showing results 1 to 20 of 160 Next >
Search Again
Page 1 of 8