Search Unity

Search Results

Search Again
Page 1 of 2
  1. seyyedmahdi69
    Post

    Question Evolutionary approach VS. "Intelligent design" for agent?

    @Luke-Houlihan I think the conversation I started didn't get across to you so I'll ask here :D could you kindly upload the modified project files?...
    Post by: seyyedmahdi69, Jan 31, 2021 in forum: ML-Agents
  2. seyyedmahdi69
    Post

    Question Evolutionary approach VS. "Intelligent design" for agent?

    So far I understood that I was missing some necessary observations. Also that you have increased size of vector actions branches and vector...
    Post by: seyyedmahdi69, Jan 15, 2021 in forum: ML-Agents
  3. seyyedmahdi69
    Post

    Question Sustainably chopping wood

    Based on your Sensor data, I am still unclear as to whether or not the agent has any idea that the forest even exists at a certain location. if...
    Post by: seyyedmahdi69, Jan 14, 2021 in forum: ML-Agents
  4. seyyedmahdi69
    Post

    Question Evolutionary approach VS. "Intelligent design" for agent?

    This is some serious result man. I didn't get there myself. So as I understood you passed in the target's location as an observation. is that...
    Post by: seyyedmahdi69, Jan 14, 2021 in forum: ML-Agents
  5. seyyedmahdi69
    Post

    Question Evolutionary approach VS. "Intelligent design" for agent?

    As before, a great pleasure to learn from you. Please let me know if you could make heads or tails from my project. Tnx.
    Post by: seyyedmahdi69, Jan 11, 2021 in forum: ML-Agents
  6. seyyedmahdi69
    Post

    Question Evolutionary approach VS. "Intelligent design" for agent?

    @Luke-Houlihan thank you very much for your inputs and opening my eyes to the things I need to learn. UPDATE SINCE MY LAST POST: I am almost...
    Post by: seyyedmahdi69, Jan 8, 2021 in forum: ML-Agents
  7. seyyedmahdi69
    Post

    Question Sustainably chopping wood

    Hi. In my humble opinion, this is definitely a simple enough problem for the agent to be able to solve. However the situation is still a little...
    Post by: seyyedmahdi69, Jan 8, 2021 in forum: ML-Agents
  8. seyyedmahdi69
    Post

    Question Evolutionary approach VS. "Intelligent design" for agent?

    UPDATE: So I have: 1- Adjusted and possibly optimized the reward system. 2- added some curiosity reward as follows: curiosity: strength:...
    Post by: seyyedmahdi69, Jan 7, 2021 in forum: ML-Agents
  9. seyyedmahdi69
    Post

    Question Evolutionary approach VS. "Intelligent design" for agent?

    thank you for the time and effort :) This amount of information just blew up in my face haha. I feel like I don't know anything at this point lol....
    Post by: seyyedmahdi69, Jan 6, 2021 in forum: ML-Agents
  10. seyyedmahdi69
    Post

    Question Evolutionary approach VS. "Intelligent design" for agent?

    Thank you for your input I remember that episode lol. But are you suggesting that my reward structure isn't the best for this problem (or just...
    Post by: seyyedmahdi69, Jan 5, 2021 in forum: ML-Agents
  11. seyyedmahdi69
    Post

    Question Evolutionary approach VS. "Intelligent design" for agent?

    Thank you very much for your input. I would have preferred for the agent to actually find the target without knowing the position but worst case...
    Post by: seyyedmahdi69, Jan 5, 2021 in forum: ML-Agents
  12. seyyedmahdi69
    Post

    Resolved Agent can't figure out how to walk around a wall

    Normalizing the data prevents something called exploding gradient in which (long story short), the network has a really bad time trying decide...
    Post by: seyyedmahdi69, Jan 3, 2021 in forum: ML-Agents
  13. seyyedmahdi69
    Post

    Resolved Agent can't figure out how to walk around a wall

    I did the same with a couple of changes. First its a good practice to normalize the input, so you might wanna set normalize to true in the yaml...
    Post by: seyyedmahdi69, Jan 3, 2021 in forum: ML-Agents
  14. seyyedmahdi69
    Post

    Resolved Agent can't figure out how to walk around a wall

    @MrpHDanny no problem haha I am pretty sure you're better at it than I am. I'll get back to you with the result.
    Post by: seyyedmahdi69, Jan 3, 2021 in forum: ML-Agents
  15. seyyedmahdi69
    Post

    Resolved Agent can't figure out how to walk around a wall

    @MrpHDanny I couldn't load the video fam. said its private. If its not a privacy problem, I'd be happy to take a look at the actual project, see...
    Post by: seyyedmahdi69, Jan 3, 2021 in forum: ML-Agents
  16. seyyedmahdi69
    Post

    Resolved Agent can't figure out how to walk around a wall

    @MrpHDanny I've only used Physics.OverlapBox() to search for a suitable spawning location in random spawning scenarios so I am not sure how it...
    Post by: seyyedmahdi69, Jan 3, 2021 in forum: ML-Agents
  17. seyyedmahdi69
    Post

    Resolved Agent can't figure out how to walk around a wall

    @MrpHDanny are you sure about this bit? if (hitColliders[0].name == "Wall") SetReward(-0.1f); I think there could be a potential...
    Post by: seyyedmahdi69, Jan 3, 2021 in forum: ML-Agents
  18. seyyedmahdi69
    Post

    Resolved Agent can't figure out how to walk around a wall

    hi @MrpHDanny and my pleasure. Firstly, its is a little unclear to me as to why you would use two raycast components if they don't have different...
    Post by: seyyedmahdi69, Jan 3, 2021 in forum: ML-Agents
  19. seyyedmahdi69
    Thread

    Question Evolutionary approach VS. "Intelligent design" for agent?

    Hi. I apologize if this question isn't really fit for a "machine learning" problem but since I doubt I can ask it anywhere else, here it goes: So...
    Thread by: seyyedmahdi69, Jan 3, 2021, 18 replies, in forum: ML-Agents
  20. seyyedmahdi69
    Post

    Agent does not solve relative simple longterm task

    Hi. my humble self would think the issue could be that the robot has no "memory" if you'd like, of the tiles it has traversed because to my...
    Post by: seyyedmahdi69, Jan 3, 2021 in forum: ML-Agents
Showing results 1 to 20 of 25 Next >
Search Again
Page 1 of 2