Search Unity

Search Results

Search Again
  1. ReinierJ
    Post

    Getting "Fewer Observations made than vector observation size" error during training

    This never happened to me, so without any further information (such as the code in your CollectObservations method) I'm afraid it's hard to...
    Post by: ReinierJ, Sep 7, 2020 in forum: ML-Agents
  2. ReinierJ
    Post

    Question External Inference (in Python)

    Internally, ml-agents uses TensorFlow. It creates a .nn file. This .nn file is not in the ONNX format, but a custom (Barracuda) format. So you...
    Post by: ReinierJ, Sep 7, 2020 in forum: ML-Agents
  3. ReinierJ
    Post

    Getting "Fewer Observations made than vector observation size" error during training

    This warning means that during execution of your CollectObservations method, you provide fewer observations with AddObservation than you specified...
    Post by: ReinierJ, Aug 31, 2020 in forum: ML-Agents
  4. ReinierJ
    Post

    Question External Inference (in Python)

    Yes this is possible, but currently not supported by the ml-agents developers. You can use inference tools that support ONNX or TensorFlow models...
    Post by: ReinierJ, Aug 31, 2020 in forum: ML-Agents
  5. ReinierJ
    Post

    Help with sidechannel

    Can you open an issue for this on GitHub so it can get fixed? https://github.com/Unity-Technologies/ml-agents/issues
    Post by: ReinierJ, Aug 31, 2020 in forum: ML-Agents
  6. ReinierJ
    Post

    Help with sidechannel

    In the SideChannel class, the OnMessageReceived method is protected, not public. Try protected override void OnMessageReceived instead of public...
    Post by: ReinierJ, Aug 28, 2020 in forum: ML-Agents
  7. ReinierJ
    Post

    Question Heuristics always gives same value

    Since you say it sounds like the Debug.Log statement at the end of the Heuristics function is working. In that case, your assumption that the...
    Post by: ReinierJ, Aug 28, 2020 in forum: ML-Agents
  8. ReinierJ
    Post

    What is difference between SetReward() and AddReward()

    With SetReward you set the reward of a specific step during learning. With AddReward you add a value to the current reward value of that step. You...
    Post by: ReinierJ, Aug 27, 2020 in forum: ML-Agents
  9. ReinierJ
    Post

    Learning Rate, Epsilon and Policy Loss

    Hi, Your understanding of the learning rate and epsilon are correct! Policy loss is not a direct indication of how much the policy changed....
    Post by: ReinierJ, Aug 27, 2020 in forum: ML-Agents
  10. ReinierJ
    Thread

    Question Structure of the output neural network

    Hello all, Is there any documentation or rationale about the structure of the neural networks that result from training? For example, one of the...
    Thread by: ReinierJ, Aug 27, 2020, 0 replies, in forum: ML-Agents
Showing results 1 to 10 of 10
Search Again