Search Unity

Search Results

Search Again
Page 1 of 15
  1. celion_unity
    Post

    Showcase #tips_cmd time scale control command

    I was looking into this the other day. ML-Agents is doing what it says it's doing (it sets Time.timeScale to the value passed for --time-scale)....
    Post by: celion_unity, May 11, 2021 in forum: ML-Agents
  2. celion_unity
    Post

    Question Handling multi profile/class agents

    Hi @The-Trope, I talked with some folks that are more familiar with goal signals, and they still think it should help with training in this sort...
    Post by: celion_unity, May 10, 2021 in forum: ML-Agents
  3. celion_unity
    Post

    Question I have a question about using a poca trainer.

    The team is still working on a submission to arxiv, and there's nothing else to share right now. When the arvix paper is available, I'll update you.
    Post by: celion_unity, May 10, 2021 in forum: ML-Agents
  4. celion_unity
    Post

    Using .onnx file or .pt file in real life

    These sort of questions are why we don't offer any support on this :) It sounds like it would be straightforward to match the output of the...
    Post by: celion_unity, Apr 29, 2021 in forum: ML-Agents
  5. celion_unity
    Post

    Match 3 Agent GC bug

    Great, the new version came out on Tuesday. Note that the Match3 code is now part of com.unity.ml-agents (not the extensions package), and also...
    Post by: celion_unity, Apr 29, 2021 in forum: ML-Agents
  6. celion_unity
    Post

    Question Problems with versions

    Which version of the python library were you using? Was the checkpoint generated from the same version? (there's a check for this but I don't see...
    Post by: celion_unity, Apr 29, 2021 in forum: ML-Agents
  7. celion_unity
    Post

    When learning Match3, the award in the built-in Unity ML-Agents algorithm is different from the awar

    You don't need to change the action mask, but I don't think there's any way for gym to use it, so you should provide it as an observation instead....
    Post by: celion_unity, Apr 29, 2021 in forum: ML-Agents
  8. celion_unity
    Post

    Question Behavioural Cloning with Gail agent behaving wired

    Hi, A few thoughts on your configuration: * I don't think you need curiosity for a racing game, I would recommend removing it. * With extrinsic...
    Post by: celion_unity, Apr 29, 2021 in forum: ML-Agents
  9. celion_unity
    Post

    Question Handling multi profile/class agents

    Hi, We added a feature in the latest release called "Goal Signals" that might help with this. The section in the documentation is here. Note that...
    Post by: celion_unity, Apr 28, 2021 in forum: ML-Agents
  10. celion_unity
    Post

    Using .onnx file or .pt file in real life

    Hi, This should be possible, but it's not an area where we can give much guidance or help with debugging. Assuming you can run an ONNX model on...
    Post by: celion_unity, Apr 27, 2021 in forum: ML-Agents
  11. celion_unity
    Post

    When learning Match3, the award in the built-in Unity ML-Agents algorithm is different from the awar

    Hi, Are you using the example scene here? I think what's happening is gym has no concept of "masked" discrete actions. We use these a lot for the...
    Post by: celion_unity, Apr 26, 2021 in forum: ML-Agents
  12. celion_unity
    Post

    Unity ML Ray Perception Sensor

    Hi, If you have a RayPerception Sensor Component attached to the Agent, the observations will automatically be collected and processed by the...
    Post by: celion_unity, Apr 26, 2021 in forum: ML-Agents
  13. celion_unity
    Post

    Train ML-Agents on built binary without using --env

    This isn't something we support right now - if you don't specify --env, mlagents-learn will assume that you're trying to connect to the editor,...
    Post by: celion_unity, Apr 26, 2021 in forum: ML-Agents
  14. celion_unity
    Post

    Question Agent REALLY seems to like walls...unless it can *see* the goal in RayPerceptionSensor?

    Sorry for the delayed response, but glad you got it sorted out...
    Post by: celion_unity, Apr 26, 2021 in forum: ML-Agents
  15. celion_unity
    Post

    Summaries cause pauses in training with multiple agents

    The summary steps should be very fast; they just compute averages on a few arrays of numbers, and then pass the results off to things like...
    Post by: celion_unity, Apr 26, 2021 in forum: ML-Agents
  16. celion_unity
    Post

    Question Problems with versions

    Hi @eseller - No problem, your English is great :) You should just need to remove the "network_settings:" section underneath the...
    Post by: celion_unity, Apr 24, 2021 in forum: ML-Agents
  17. celion_unity
    Post

    Some advice and suggestions. (python status, MaxStep vs MaxEnvironmentSteps and ray sensor useage)

    Thanks for catching the soccer setup problem. The agents shouldn't have their MaxStep set. A PR to fix that is here...
    Post by: celion_unity, Apr 22, 2021 in forum: ML-Agents
  18. celion_unity
    Post

    Some advice and suggestions. (python status, MaxStep vs MaxEnvironmentSteps and ray sensor useage)

    This is a good feature request, but not something that's easy to add right now. In the meantime, I would recommend using the existing curriculum...
    Post by: celion_unity, Apr 22, 2021 in forum: ML-Agents
  19. celion_unity
    Post

    Question I have a question about using a poca trainer.

    I talked to the research folks some more. The high-level explanation is that POCA trains a group of agents to maximize a shared common reward. It...
    Post by: celion_unity, Apr 21, 2021 in forum: ML-Agents
  20. celion_unity
    Post

    Question I have a question about using a poca trainer.

    Hi @xogur6889, The POCA algorithm was developed by the ML-Agents research team. They're working on an arxiv submission, but it's not ready yet....
    Post by: celion_unity, Apr 21, 2021 in forum: ML-Agents
Showing results 1 to 20 of 289 Next >
Search Again
Page 1 of 15