{ "id": 191256, "title": "more details on how the data was generated", "url": "/competitions/conways-reverse-game-of-life-2020/discussion/191256", "author_name": "", "post_date": "2020-10-15T14:37:33.246595300Z", "votes": null, "comment_count": 2, "views": 0, "content": "

The \"Data\" section reads:

\n
\n

Your test-set predictions should be the starting board at delta steps before the stopping board. The games were created by the following procedure:

\n
    \n
  1. An initial board was chosen by filling the board with a random density between 1% full (mostly zeros) and 99% full (mostly ones).
    2. \n
  2. This initial board was evolved 5 steps.
    3. \n
  3. The starting board's state was recorded after the 5 \"warmup steps\". These are the values in the start variables.
    4. \n
  4. The starting board was then evolved delta steps. Delta was chosen to be uniformly random between 1 and 5. If the stopping board was empty, the game was discarded.
    5. \n
  5. The stopping board's state was then recorded. These are the values in the stop variables.
    6. \n
\n
\n

In terms of step 1, is it that first a uniform random variable between 0.01 to 0.99 is picked, and then a board is generated where each cell independently has this probability to be live?

\n

Or is it something else?

", "messages": [ { "id": "1050555", "postDate": "10/15/2020 14:37:33", "content": "

The \"Data\" section reads:

\n
\n

Your test-set predictions should be the starting board at delta steps before the stopping board. The games were created by the following procedure:

\n
    \n
  1. An initial board was chosen by filling the board with a random density between 1% full (mostly zeros) and 99% full (mostly ones).
    2. \n
  2. This initial board was evolved 5 steps.
    3. \n
  3. The starting board's state was recorded after the 5 \"warmup steps\". These are the values in the start variables.
    4. \n
  4. The starting board was then evolved delta steps. Delta was chosen to be uniformly random between 1 and 5. If the stopping board was empty, the game was discarded.
    5. \n
  5. The stopping board's state was then recorded. These are the values in the stop variables.
    6. \n
\n
\n

In terms of step 1, is it that first a uniform random variable between 0.01 to 0.99 is picked, and then a board is generated where each cell independently has this probability to be live?

\n

Or is it something else?

", "rawMarkdown": "The \"Data\" section reads:\n\n> Your test-set predictions should be the starting board at delta steps before the stopping board. The games were created by the following procedure:\n\n> 1. An initial board was chosen by filling the board with a random density between 1% full (mostly zeros) and 99% full (mostly ones).\n2. This initial board was evolved 5 steps.\n3. The starting board's state was recorded after the 5 \"warmup steps\". These are the values in the start variables.\n4. The starting board was then evolved delta steps. Delta was chosen to be uniformly random between 1 and 5. If the stopping board was empty, the game was discarded.\n5. The stopping board's state was then recorded. These are the values in the stop variables.\n\nIn terms of step 1, is it that first a uniform random variable between 0.01 to 0.99 is picked, and then a board is generated where each cell independently has this probability to be live? \n\nOr is it something else?", "votes": null }, { "id": "1050791", "postDate": "10/15/2020 18:22:12", "content": "

Yes, you explained it right. A number between 0.01 and 0.99 is picked at random and each cell on the board has that number as the probability of being 1. So if you were to take the ratio of cells filled with 1 to the total number of cells, you will get close to that chosen number between 0.01 and 0.99.

\n

For example, if the probability picked was 0.10, you will find that approx. 10 out of 100 cells would be 1 in the initial state.

", "rawMarkdown": "Yes, you explained it right. A number between 0.01 and 0.99 is picked at random and each cell on the board has that number as the probability of being 1. So if you were to take the ratio of cells filled with 1 to the total number of cells, you will get close to that chosen number between 0.01 and 0.99.\n\nFor example, if the probability picked was 0.10, you will find that approx. 10 out of 100 cells would be 1 in the initial state.", "votes": null }, { "id": "1051313", "postDate": "10/16/2020 11:27:17", "content": "

Great! Thanks :)

", "rawMarkdown": "Great! Thanks :)", "votes": null } ], "comments": [ { "id": 1050791, "author_name": "rude009", "author_url": "", "post_date": "10/15/2020 18:22:12", "content": "

Yes, you explained it right. A number between 0.01 and 0.99 is picked at random and each cell on the board has that number as the probability of being 1. So if you were to take the ratio of cells filled with 1 to the total number of cells, you will get close to that chosen number between 0.01 and 0.99.

\n

For example, if the probability picked was 0.10, you will find that approx. 10 out of 100 cells would be 1 in the initial state.

", "votes": null, "replies": [] }, { "id": 1051313, "author_name": "claudiuds", "author_url": "", "post_date": "10/16/2020 11:27:17", "content": "

Great! Thanks :)

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "1050555": "The \"Data\" section reads:\n\n> Your test-set predictions should be the starting board at delta steps before the stopping board. The games were created by the following procedure:\n\n> 1. An initial board was chosen by filling the board with a random density between 1% full (mostly zeros) and 99% full (mostly ones).\n2. This initial board was evolved 5 steps.\n3. The starting board's state was recorded after the 5 \"warmup steps\". These are the values in the start variables.\n4. The starting board was then evolved delta steps. Delta was chosen to be uniformly random between 1 and 5. If the stopping board was empty, the game was discarded.\n5. The stopping board's state was then recorded. These are the values in the stop variables.\n\nIn terms of step 1, is it that first a uniform random variable between 0.01 to 0.99 is picked, and then a board is generated where each cell independently has this probability to be live? \n\nOr is it something else?", "1050791": "Yes, you explained it right. A number between 0.01 and 0.99 is picked at random and each cell on the board has that number as the probability of being 1. So if you were to take the ratio of cells filled with 1 to the total number of cells, you will get close to that chosen number between 0.01 and 0.99.\n\nFor example, if the probability picked was 0.10, you will find that approx. 10 out of 100 cells would be 1 in the initial state.", "1051313": "Great! Thanks :)" }, "source": "meta" }