Search Unity

Search Results

Search Again
Page 1 of 2
  1. seboz123
    Thread

    Question Way to visualize Ray Perception Sensor

    Hi, I was wondering, if there is an easy way to draw the Debug gizmos of the Ray Perception Sensor ingame for demonstration purposes? Thanks!
    Thread by: seboz123, Sep 28, 2020, 2 replies, in forum: ML-Agents
  2. seboz123
    Post

    Question Setting Observation space at runtime

    Thanks I will use that for now!
    Post by: seboz123, Sep 28, 2020 in forum: ML-Agents
  3. seboz123
    Thread

    Question Setting Observation space at runtime

    Hello, I am creating a maze environment and want to create an array of visited cells which serve as an vector input for the agent. As I want to...
    Thread by: seboz123, Sep 26, 2020, 2 replies, in forum: ML-Agents
  4. seboz123
    Post

    Question Buffer Size and Sensor observations

    Thanks for your fast response. Thanks for clarification! So the buffer does store all experiences right? Not only finished trajectories. No I was...
    Post by: seboz123, Aug 14, 2020 in forum: ML-Agents
  5. seboz123
    Post

    I Want to use DQN

    There is a google colab implementation of dqn....
    Post by: seboz123, Aug 14, 2020 in forum: ML-Agents
  6. seboz123
    Thread

    Question Buffer Size and Sensor observations

    Hi, I've got two seperate questions: First one regarding PPO: Why does the buffer size matter for learning? For example: Buffer size 10k and...
    Thread by: seboz123, Aug 14, 2020, 4 replies, in forum: ML-Agents
  7. seboz123
    Post

    Question Meta Learning and RL-Trainer Implementation

    I was trying to use the ml-agents trainers because of their ability to parallelize - I can run multiple agents and multiple instances of the...
    Post by: seboz123, Jul 29, 2020 in forum: ML-Agents
  8. seboz123
    Thread

    Question Meta Learning and RL-Trainer Implementation

    Hi, so I am currently using ml-agents for my thesis and trying to implement MAML and Reptile meta-learning algorithms. See:...
    Thread by: seboz123, Jul 27, 2020, 4 replies, in forum: ML-Agents
  9. seboz123
    Post

    Two-player turn-based boardgames (TicTacToe, ConnectFour, ...)

    probably u need to rename the behaviour in your yaml to the behaviour name of your unity brain. Just a quick little thing you could try
    Post by: seboz123, Jul 27, 2020 in forum: ML-Agents
  10. seboz123
    Thread

    Question Python API - num-agents

    Hi, I have a question regarding the python API. I am trying to get the total number of agents for my own algorithm. I try to just add the length...
    Thread by: seboz123, Jul 19, 2020, 1 replies, in forum: ML-Agents
  11. seboz123
    Post

    Question Parallelization of Environments

    I am using my own implementations of Algorithms so I cannot use --num-envs. That works only for ppo and sac I think, which are already implemented.
    Post by: seboz123, Jul 3, 2020 in forum: ML-Agents
  12. seboz123
    Post

    Decision Requester, policy update and time step questions

    So just for clarification: In PPO agents collect obeservations into the buffer until it is full, then sample batch size experiences and update the...
    Post by: seboz123, Jul 3, 2020 in forum: ML-Agents
  13. seboz123
    Post

    Show Saved ML Agent

    There is a model of your behavior created during the training process. You can find it in your results directory. You can then just dran and drop...
    Post by: seboz123, Jul 3, 2020 in forum: ML-Agents
  14. seboz123
    Post

    Python API vs. Gym wrapper

    Python API gives you more control, as it is for example possible to have multiple agents and multiple behaviors and control them. Also they both...
    Post by: seboz123, Jul 3, 2020 in forum: ML-Agents
  15. seboz123
    Post

    Question Parallelization of Environments

    Also another thing: I read somewhere, that you cannot use the parameter no-graphics=True when you are using physics inside the game. Is that...
    Post by: seboz123, Jul 2, 2020 in forum: ML-Agents
  16. seboz123
    Thread

    Question Parallelization of Environments

    Hi! So I have some questions regarding parallelization in ml-agents. Maybe someone can clarify these things. With the python API you are able to...
    Thread by: seboz123, Jul 2, 2020, 3 replies, in forum: ML-Agents
  17. seboz123
    Post

    Debug.Log logging

    Perfect, Thank you very much!
    Post by: seboz123, Jun 19, 2020 in forum: ML-Agents
  18. seboz123
    Post

    Debug.Log logging

    I am using: ml-agents: 0.17.0, ml-agents-envs: 0.17.0, Communicator API: 1.0.0, TensorFlow: 2.0.0 and python 3.7.7
    Post by: seboz123, Jun 18, 2020 in forum: ML-Agents
  19. seboz123
    Thread

    Debug.Log logging

    Hi, So when I build my Project as an executable and running it, it sometimes crashes. So I was wondering if there is a Log File of the Debug.Log...
    Thread by: seboz123, Jun 16, 2020, 4 replies, in forum: ML-Agents
  20. seboz123
    Post

    'UnityEnvironment' object has no attribute 'behavior_spec'

    Ok I think it is due to a different version of ml-agents. Try get_behavior_spec()
    Post by: seboz123, Jun 14, 2020 in forum: ML-Agents
Showing results 1 to 20 of 24 Next >
Search Again
Page 1 of 2