Tried out an idea to stop the agent from destroying itself at the last few lines, but it didn’t seem to have much effect, possible making it worse.
So, another avenue of exploration is to inspect the data and see if there is a pattern to it. What I will be doing is taking in various [...]

I implemented probability look-ahead play today and aam currently testing it. The biggest problem is that it takes much longer to do stuff.
The algorithm is like this:
- The current piece is evaluated in every position as per normal but its value is now made up of fractions of field values after the next piece has [...]

Well, I managed to get the proving problems sorted out (tech support for the uni end and proper username on the RL Comp end).
Here are the results:
Total Number of Episodes: 24392
Total Return: 4782563.0
Total Time taken: 24 hours, 36 minutes, 2 seconds
These results mean nothing unless put into context, i.e. my position on the leaderboard. As [...]

With the current proposed AI idea (based on pain), bots would generally avoid anything that causes them pain. The counterbalance to this is having goals to do. For instance, as a town guard, perhaps a civilian falls in the water and needs rescuing. The guard doesn’t want to get wet, but has a job to [...]

This isn’t so much of a game idea as a possible use in games. Or just a theoretical experiment for mapping movement.
By creating a model of the human body (not exact, but approximately), or even of some sort of entity, and then using RL (I love RL) or some other method of testing to test [...]