Search Unity

Search Results

Search Again
Page 1 of 3
  1. gft-ai
    Post

    Simulation of an autonomous Rock Breaker

    Congratulations! I think you can give a little variations such as varying initial position of the rock breaker body, change up the size of the...
    Post by: gft-ai, Nov 24, 2021 in forum: ML-Agents
  2. gft-ai
    Post

    Question Environment Setting during running

    Sounds like something that could be done using the side channels. See the documentation here:...
    Post by: gft-ai, Nov 23, 2021 in forum: ML-Agents
  3. gft-ai
    Post

    Simulation of an autonomous Rock Breaker

    One thing i can suggest is changing the observation from localposition of the rock and the agent to the rock’s relative distance from the agent...
    Post by: gft-ai, Nov 23, 2021 in forum: ML-Agents
  4. gft-ai
    Post

    Simulation of an autonomous Rock Breaker

    Cool thanks, your reward structure seems to be way out of the recommended range but in my experience as long as the rewards clearly indicate in...
    Post by: gft-ai, Nov 22, 2021 in forum: ML-Agents
  5. gft-ai
    Post

    Simulation of an autonomous Rock Breaker

    It would be better to provide some more informations as to how your environment setup like observations & reward structure before anyone can...
    Post by: gft-ai, Nov 21, 2021 in forum: ML-Agents
  6. gft-ai
    Post

    Ray Sensor Observation

    The answer to your question has already been answered. You can refer to:...
    Post by: gft-ai, Nov 17, 2021 in forum: ML-Agents
  7. gft-ai
    Post

    No actions being taken by this AI (MLAgents)

    I think you are using the deprecated method for onactionreceived. Can you try with OnActionReceived(ActionBuffers actions)? refer to:...
    Post by: gft-ai, Nov 17, 2021 in forum: ML-Agents
  8. gft-ai
    Post

    No actions being taken by this AI (MLAgents)

    In the script i don’t see the value defined for the jumpForce variable, are you setting that somewhere? if that is not the case then have you...
    Post by: gft-ai, Nov 10, 2021 in forum: ML-Agents
  9. gft-ai
    Post

    No actions being taken by this AI (MLAgents)

    Have you added decision requester component to the game object which this script is attached to?
    Post by: gft-ai, Nov 7, 2021 in forum: ML-Agents
  10. gft-ai
    Post

    Question How to use model ONNX trained with Rllib in Unity Editor.

    I don’t have any experience with Rllib but I have had a similar experience when converting pytorch models to onnx to use it in unity. What I did...
    Post by: gft-ai, Nov 4, 2021 in forum: ML-Agents
  11. gft-ai
    Post

    Question Apply data functions and transformations on python

    By the sound of it what you want to use is the low level API to trigger the training from the python side - where you can also implement custom...
    Post by: gft-ai, Nov 4, 2021 in forum: ML-Agents
  12. gft-ai
    Post

    How to write your own vector observation?

    So if I understand this correctly, you want to make the agents to ‘sense’ where each other is. There are raycasting libraries you can use in...
    Post by: gft-ai, Oct 1, 2021 in forum: ML-Agents
  13. gft-ai
    Post

    Need help with unity DQN reinforcement learning !!!

    It would help if you looked at the error message more carefully. it says in line 322 in environment.py, vector_action.keys() is an integer...
    Post by: gft-ai, Sep 30, 2021 in forum: ML-Agents
  14. gft-ai
    Post

    How to write your own vector observation?

    I think what you need is a raycasting sensor. If you search for raycasting sensor you will get a good idea where to start. There are also many...
    Post by: gft-ai, Sep 30, 2021 in forum: ML-Agents
  15. gft-ai
    Post

    Question Setup of MLAgents -error message attached

    I suggest you take a look at the training configuration file and see if you are missing the field the error gave you. if would probably help to...
    Post by: gft-ai, Sep 25, 2021 in forum: ML-Agents
  16. gft-ai
    Post

    "the external ONNX file data" to NNModel Instance

    I don’t quite understand what you mean? Maybe it might help if you explained what you have done and what you want to achieve? Where is this .onnx...
    Post by: gft-ai, Sep 10, 2021 in forum: ML-Agents
  17. gft-ai
    Post

    Question Unable to reach perfection in extraordinarily simple environment

    I think the max value given by Random.Range() for integers is exclusive. So I am not sure if that is the problem...
    Post by: gft-ai, Sep 9, 2021 in forum: ML-Agents
  18. gft-ai
    Post

    Which parameter affects the RAM usage for SAC?

    I guess it would depend on how ‘close’ the values are. But I would say it depends on your hardware capabilities you just have to choose the...
    Post by: gft-ai, Sep 9, 2021 in forum: ML-Agents
  19. gft-ai
    Post

    "the external ONNX file data" to NNModel Instance

    https://docs.unity3d.com/Packages/com.unity.barracuda@1.0/manual/Loading.html Does this help?
    Post by: gft-ai, Sep 8, 2021 in forum: ML-Agents
  20. gft-ai
    Post

    Which parameter affects the RAM usage for SAC?

    Probably both! you can read about them in the following link https://github.com/yosider/ml-agents-1/blob/master/docs/Training-SAC.md#buffer-size
    Post by: gft-ai, Sep 8, 2021 in forum: ML-Agents
Showing results 1 to 20 of 44 Next >
Search Again
Page 1 of 3