Download it at http://www.cs.ucla.edu/~billyh/AIFighter.zip
Source code available at http://www.cs.ucla.edu/~billyh/AIFighterCode.zip
To play you need a PC, the XNA framework that you can download here
No longer needs Xbox controllers!
Major Changes from the last version
I enabled the keyboard so that users without XBox controllers could play. Many people outside the class asked for this. Additionally, I fixed […]
As usual, you can find our latest work at
http://www.cs.ucla.edu/~billyh/AIFighter.zip
The entire project can be found at
http://www.cs.ucla.edu/~billyh/AIFightingGame.zip
In response to gameplay testing feedback [that it was difficult to train the AI and that the non-active player got bored], I’ve added a teaching mechanism for the inactive player. The inactive player controls a small “teacher” version of their […]
I gave the playtesters (friends from my lab, who hadn’t played the game) the following control directions:
Controls:
A: Attack (Fire Arrow if Bow is Drawn)
X: Block
Y: Jab
B: Power Attack
Left/Right Trigger: Draw Bow
Left/Right Shoulder: Dodge Left/Right
One playtester asked “What does dodge mean?” and they didn’t really understand how to shoot arrows.
Then they played […]
I added lots of graphics for the AI, added a title screen, and added a background. Don’t worry, I will add the bow graphics. These animations are taking a very very long time to make. I’d rather take the time to make it look good.
I’m pretty happy with the progress this week. The AI observes the human player, constructs data points based on player actions and the state of the world when the player performs the actions, then builds a decision tree based on what the player does.
Between rounds I print out the decision tree. It’s pretty […]
This is our first demo that’s playable from beginning to end. It is obviously lacking an AI that learns (as well as walls, camera work, powerups, and a whole bunch of polish).
http://www.cs.ucla.edu/~billyh/AIFighter.zip
Find it at http://www.cs.ucla.edu/~billyh/AIFighterGame.zip
This is an attempt to help visualize how this game will turn out. These are more of suggestions rather than concrete ideas of how the game should be when it’s finished.
This is the training process. After some time, the AI will pick up on the players fighting style and ask questions about how it should […]
The math here is mostly taken from Russell and Norvig, the quintessential AI book.
For AIFighter, the AIs must learn from the player’s actions how to fight. There are two types of primitives, actions and conditions. Actions are available moves character (AI or human alike) can perform, like Swing Sword or Move Towards Opponent. Conditionals are […]