Search Unity

Search Results

Search Again
Page 1 of 3
  1. mcdenyer
    Thread

    Question High level steps to allow users to upload a replay to social media

    Looking for some strategies to go from some replay game data -> uploading a replay to social media. I'm using unity 2019.
    Thread by: mcdenyer, Jul 26, 2023, 0 replies, in forum: Audio & Video
  2. mcdenyer
    Post

    Question Addressables for Level Packs

    @Jribs The 'download a bunch at once' part is it possible to do that a single time or do they have to download them all every time the reopen the app?
    Post by: mcdenyer, Jul 19, 2023 in forum: Addressables
  3. mcdenyer
    Thread

    Question Addressables for Level Packs

    I am trying to better understand Addressables/Asset Bundles I want the user to be able to reach points in my game where another say 100 levels is...
    Thread by: mcdenyer, Jul 6, 2023, 3 replies, in forum: Addressables
  4. mcdenyer
    Post

    Bug Training freezing every 10.000 steps for 60-80 seconds

    @Thorce I was only able to cut 30 minutes off a 9hour run by using the GPU and I have a much larger network than you so I'd think I would see even...
    Post by: mcdenyer, Jun 25, 2023 in forum: ML-Agents
  5. mcdenyer
    Post

    Bug Training freezing every 10.000 steps for 60-80 seconds

    interesting @Thorce I will have to try that out.
    Post by: mcdenyer, Jun 24, 2023 in forum: ML-Agents
  6. mcdenyer
    Post

    Bug Training freezing every 10.000 steps for 60-80 seconds

    @Luke-Houlihan it's been my understanding that CPU > GPU for PPO, am I wrong?
    Post by: mcdenyer, Jun 23, 2023 in forum: ML-Agents
  7. mcdenyer
    Thread

    Discussion Calculating Optimal Reward function for checkpoint based reqward system

    I am training agents to go from the start of my level to the end of the level. I am trying to figure out how to calculate an optimal reward...
    Thread by: mcdenyer, Jun 22, 2023, 0 replies, in forum: ML-Agents
  8. mcdenyer
    Post

    Question Are Ray Perception Sensors Observation Normalized?

    @GamerLordMat I think you are correct. I think I am getting a boost on the first half of the level from the auto-normalization because the bounds...
    Post by: mcdenyer, Jun 1, 2023 in forum: ML-Agents
  9. mcdenyer
    Post

    Question Are Ray Perception Sensors Observation Normalized?

    https://forum.unity.com/threads/how-to-get-value-of-distance-between-agent-obstacles-with-using-rayperceptionsensor3d.1043338/ @Luke-Houlihan in...
    Post by: mcdenyer, Jun 1, 2023 in forum: ML-Agents
  10. mcdenyer
    Post

    Question Are Ray Perception Sensors Observation Normalized?

    I'm curious why they would not normalize these using the ray distance. I think I must be getting a large benefit from that.
    Post by: mcdenyer, May 30, 2023 in forum: ML-Agents
  11. mcdenyer
    Thread

    Question Extrinsic Reward Neural Network Architecture

    I havn't been able to find much about how to go about configuring the architecture for the reward signal networks. In fact I cannot understand at...
    Thread by: mcdenyer, May 30, 2023, 0 replies, in forum: ML-Agents
  12. mcdenyer
    Post

    Question Are Ray Perception Sensors Observation Normalized?

    I assume that they are in fact normalized but I am just puzzled how I am getting better results from using the python normalization versus doing...
    Post by: mcdenyer, May 28, 2023 in forum: ML-Agents
  13. mcdenyer
    Post

    Question Are Ray Perception Sensors Observation Normalized?

    Yes but I am talking about the RaySensor 2d Component that comes packaged with unity ML Agents.
    Post by: mcdenyer, May 28, 2023 in forum: ML-Agents
  14. mcdenyer
    Thread

    Question Are Ray Perception Sensors Observation Normalized?

    I have been manually normalizing all my vector observations and wasn't using the normalization hyperparamter. I tried flipping on normalization...
    Thread by: mcdenyer, May 24, 2023, 8 replies, in forum: ML-Agents
  15. mcdenyer
    Post

    Question Associating rewards with past actions

    So I used to think that lambda effected this but I don't think it's so simple and I would suggest not touching it just yet. I also have seem some...
    Post by: mcdenyer, May 19, 2023 in forum: ML-Agents
  16. mcdenyer
    Thread

    Question How to distinguish between overfitting, local maximum, and just needing to train longer

    When training stalls out at a certain point in my levels I'm trying to diagnose what is happening so I can try and tweak hyperparamters accordingly
    Thread by: mcdenyer, May 19, 2023, 1 replies, in forum: ML-Agents
  17. mcdenyer
    Thread

    Question Normalize hyerparamter VS manualy normalizing your observations

    I have always normalized my observations myself. Is there some extra benefit to using the normalize hyperparamter over just normalizing yourself?
    Thread by: mcdenyer, May 19, 2023, 0 replies, in forum: ML-Agents
  18. mcdenyer
    Thread

    Discussion Best AMIs For Training on AWS EC2 Instance for PPO policy

    I want to train on EC2 Instances, mainly for the purpose of hyper parameter tuning so that I can test many different sets of hyper parameters on...
    Thread by: mcdenyer, May 9, 2023, 0 replies, in forum: ML-Agents
  19. mcdenyer
    Thread

    Feedback Agents reaching end of level(max reward) but not learning from it.

    Below is an image of the Cumulative Reward Graph. The max reward is 3.1(end of the level) as you can see the agent is reaching the 3.1 point at...
    Thread by: mcdenyer, Jan 19, 2022, 2 replies, in forum: ML-Agents
  20. mcdenyer
    Post

    Question Is there a general sequence in which the configurations should be tweaked?

    And what guides your of time_horizon setting? When I originally looked at time_horizon i was excited because I need my agents to 'understand'...
    Post by: mcdenyer, Jan 17, 2022 in forum: ML-Agents
Showing results 1 to 20 of 48 Next >
Search Again
Page 1 of 3