Design a game that is good for a neural network
Forum Reply
11 years, 6 months ago
Highlights
Hi, I suggest that you take a look at Temporal Difference Learning, where the AI is trained to Grand Master level by Reinfoced Learning (nnet's learn by playing against itself).…
11 years, 6 months ago
Pacman ghost ai
Forum Reply
11 years, 8 months ago
Instead of checking for direction every frame, you could base the checking on a probability based on e.g. perlin noise. You could also make the gost move 'physically' i.e. it ta…
11 years, 8 months ago
Fitness function for self modifying programming
Forum Reply
12 years ago
Karl Simms had great success with pure generic algorithms, the "programs" are boolean logic components that evolve genetically (pdf). I haven't tried, but I think it might work…
12 years ago
Latest Activity
See all in DiscussionsHi, I suggest that you take a look at Temporal Difference Learning, where the AI is trained to Grand Master …
11 years, 6 months ago
Instead of checking for direction every frame, you could base the checking on a probability based on e.g. perlin noise. …
11 years, 8 months ago
Karl Simms had great success with pure generic algorithms, the "programs" are boolean logic components that evolve genetically (pdf). I …
12 years ago
Badges
Decade Member
5-Year Veteran
1-Year Veteran
Spotlight
Jack-of-Trades
View all badges →