Search Unity

Search Results

Search Again
Page 1 of 2
  1. TulioMMo
    Post

    Question Hybrid Control (Discrete + Continuous actions)

    Well, I think I got it: Since the probability ratios of continuous and discrete actions are being multiplied against each other, that is probably...
    Post by: TulioMMo, Jun 22, 2022 in forum: ML-Agents
  2. TulioMMo
    Post

    Question Hybrid Control (Discrete + Continuous actions)

    Sorry for resuscitating this post after so long. I wanted to know if the final layer for the actor neural nework in PPO follows the same logic as...
    Post by: TulioMMo, Jun 2, 2022 in forum: ML-Agents
  3. TulioMMo
    Post

    Question Force epsilon to lower values than 0.1

    Thank you very much for the reply! I'll try it out.
    Post by: TulioMMo, Mar 22, 2022 in forum: ML-Agents
  4. TulioMMo
    Thread

    Question Force epsilon to lower values than 0.1

    As noticed in https://github.com/Unity-Technologies/ml-agents/issues/4984, the lowest value allowed for epsilon during training is 0.1. It does...
    Thread by: TulioMMo, Mar 10, 2022, 2 replies, in forum: ML-Agents
  5. TulioMMo
    Post

    Question Increase in memory_size decreasing cumulative reward

    Thank you for your reply! And I apologise for the colours I picked. I'll be more careful next time. Ideally tensorboard could give the option of...
    Post by: TulioMMo, Mar 8, 2022 in forum: ML-Agents
  6. TulioMMo
    Post

    Action masking in binary case

    I don´t think you need to use action masking in this case. You could set a state for the agent so it can differentiate between your drop station...
    Post by: TulioMMo, Mar 8, 2022 in forum: ML-Agents
  7. TulioMMo
    Thread

    Question Increase in memory_size decreasing cumulative reward

    I am experimenting with LSTM in my project and I found an odd behaviour. By keeping sequence_length constant ( = 16), increasing memory_size is...
    Thread by: TulioMMo, Mar 8, 2022, 2 replies, in forum: ML-Agents
  8. TulioMMo
    Post

    Question Train 2 or more Unity projects simultaneously

    Many thanks! changing the base port number did the trick. :)
    Post by: TulioMMo, Feb 23, 2022 in forum: ML-Agents
  9. TulioMMo
    Post

    Question Train 2 or more Unity projects simultaneously

    Sorry, problem was not solved. I managed to train two projects by running one training session in Unity Editor and another with a built...
    Post by: TulioMMo, Feb 23, 2022 in forum: ML-Agents
  10. TulioMMo
    Post

    Question Train 2 or more Unity projects simultaneously

    Guess it was obvious, but I found a way to do it with these links:...
    Post by: TulioMMo, Feb 23, 2022 in forum: ML-Agents
  11. TulioMMo
    Thread

    Question Train 2 or more Unity projects simultaneously

    Hi everyone, I am trying to train 2 (or more) projects simultaneously in Unity ML-Agents, but have received the warning: "Couldn't start socket...
    Thread by: TulioMMo, Feb 21, 2022, 4 replies, in forum: ML-Agents
  12. TulioMMo
    Post

    Official Post Your ML-Agents Project

    I have recently published a journal article at Ocean Engineering. I used Unity ML-Agents to train a tidal lagoon environment with random generated...
    Post by: TulioMMo, Feb 20, 2022 in forum: ML-Agents
  13. TulioMMo
    Post

    Question Warning when using LSTM

    It would be nice to have an official confirmation, but it seems this error is a false alarm and the outputted neural network is valid:...
    Post by: TulioMMo, Feb 20, 2022 in forum: ML-Agents
  14. TulioMMo
    Post

    Question LSTM Unity ML-Agents

    Thank you very much for the thorough answer and links!! I run some experiments with your suggestions.
    Post by: TulioMMo, Feb 7, 2022 in forum: ML-Agents
  15. TulioMMo
    Post

    Question LSTM Unity ML-Agents

    Thank you very much! I had misunderstood the concept of "memory_size". I have some other questions, though.. 1) Assuming an example where I have...
    Post by: TulioMMo, Feb 3, 2022 in forum: ML-Agents
  16. TulioMMo
    Post

    What is the meaning of "network_settings -> normalize" in Configurations

    During Inference is the "test data" being normalised as well? Does the onnx file keeps a record of the average and variance from the training data...
    Post by: TulioMMo, Feb 2, 2022 in forum: ML-Agents
  17. TulioMMo
    Thread

    Question LSTM Unity ML-Agents

    Hi Everyone, I am trying to use LSTM in my project (using PPO), but I have a couple of questions. 1st: Are there any suggestions when choosing...
    Thread by: TulioMMo, Jan 28, 2022, 5 replies, in forum: ML-Agents
  18. TulioMMo
    Post

    Question Hybrid Control (Discrete + Continuous actions)

    Thank you very much!! I'll try one more time with your suggestion
    Post by: TulioMMo, May 14, 2021 in forum: ML-Agents
  19. TulioMMo
    Post

    Question Hybrid Control (Discrete + Continuous actions)

    Hmm, maybe I am doing something wrong... Right now I am using powerInputPumping = Mathf.Clamp(actionBuffers.ContinuousActions[0], 0f, 1f) *...
    Post by: TulioMMo, May 11, 2021 in forum: ML-Agents
  20. TulioMMo
    Post

    Question Hybrid Control (Discrete + Continuous actions)

    I am developing a research project that simulates the operation of hydraulic bulb turbines under ocean signal, where the goal is to maximize the...
    Post by: TulioMMo, May 10, 2021 in forum: ML-Agents
Showing results 1 to 20 of 29 Next >
Search Again
Page 1 of 2