5/11*********************************************************************
AI UPDATE:
The Artificial Intelligence used in KungFu Tamagotchi is a reinforcement learning
based algorithm. It is highly configurable in its ability to take different types of
game state information on which to learn on. One typical problem with seen with standard
reinforcement algorithms is the unmanageable size of the Q-Table which is partially avoided
in this implementation through the use of a Q-Tree. The Q-Tree is a decision tree where the
decision variables correspond to different game state variables. So we can construct a Q-Tree
by first examining the `Distance to the Opponent`, and then branching on the `Opponent's current
move` to arrive at a Q-State. The benefit of this approach is that we can store Q-States as we
see them (saving memory), and have the possibility of dynamically aggregating similar states together.

In terms of the AI learning process, reinforcement is given both by the environment as well
as by the user. The AI is positively rewarded for successfully landing an attack on its opponent,
and negatively reinforced for being hit automatically. Therefore in theory, the AI can learn on its
own without user interaction. The problem with this unguided approach is that Q-Learning takes a long
time to fully and accurately explore the state/action space. The user therefore comes in to shortcut
the exploration process by showing the AI what do to. The user can take two routes in this, the first
is to actually dictate the AI's next move, and the second is to reinforce the AI's last action. With
both automatic environment learning and user guided learning, we think our AI will provide new and
interesting results.


Microsoft Speech Recognition SDK: integrated and working
In the fighting mode users can call the moves into the microphone and the player will perform the
specific move. The user can also call things such as "Next Round" or "Start Game" and the game
will proceed to the corresponding command.



5/5*********************************************************************
Development:
Move Creation UI: New functionality:
1. Allowed mulitple selection and manipulation of pullpoints
2. Added copy/paste of poses
3. Added time manipulation information
4. Added labels and refined layout
5. Added Attacking limb
6. Added Attack Target





Fighting/Training UI: New functionality/Improvements:
Heads up Display/Graphics:
-health bars appear at top
-displays clock
-displays round #
-end of game displays winner
-you can select the # of rounds for a game
-you can select the length of a round





4/28:*********************************************************************
The Great Mergenation… (Something like integration, but not…)

Integrated AI in Fighting/Training Mode:

Now the physics has some control over gravity so players don't
levitate, but doesn't work so well with integrated AI testing. One
issue is that the pull points move too fast. Next iteration, the pull
points will move relative to an average time step.

Attacking sort of works, but still has issues with knowing when it is
done. Also attacks don't pack much punch so to make it look nicer
We've amplified the strength of an attack upon collision. Had a lot of
craziness with forces being applied for just touching so we put a
threshold on how strong an attack has to be to constitute an attack.
It has to be strong solid hit, which makes sense for figuring out
damage. Still needs a bit of tweaking, but fighters will push each
other away if they get to close.

Also if the fighter moves to far away from his pull points they will
stop pulling and move towards him.

KICK!!!!



PUNCH!!!



4/21:*********************************************************************
Development:
AI:Working on integrating the current AI infrastructure with the physics
moves for the Marionette players.
Move Creation UI: Iteration 3 of move creation interface complete.
You can currently create new moves and configurations for each of
the moves. When you add a pose, you can edit the relative X, Y and
Z coordinates of the pull points, and you can select multiple pull
points at a time.

Coming soon: Adding timestep information so you can customize the
length of an action. Additionally, you'll be able to copy and paste
configurations.




Fighting/Training UI: New functionality:

Game Controls:
-At the beginning you load two players
-List of available moves is on the right side of the screen
-hit corresponding key to select a move
-After each round, press SPACEBAR for next round
-After each match, press ENTER start a new game







4/14:*********************************************************************
Development:
Move and Fighting UIs: Iteration 2 of 2D interfaces ready for testing.
AI: Demo AI architecture in class, basic learning technique modeled and
executed by balls.
Currently we are updating the AI infrastructure to be more flexible in how it
partitions the state space within the Q-Value tree. Demo of AI works within a
miny rolling balls game, where the goal is for the AI enabled ball to learn
how to hit the other ball.



4/7:*********************************************************************
Development:
Move and Fighting UIs: Prototype move creation system implemented, ready for testing.
AI: Simplified AI architecture implemented, ready for testing.
Physics/Graphics Engine: Iteration 2 marionette engine test bed complete.
The marionette has circles around the figure represenation the pull points.
Each pull point is associated with a joint of the marionette.


Graphics: Created Maps for the environment using GtkRadiant.
We are having problems loading the maps into Dojo since it changes the
the color values and we haven't figured out how/why?







3/31:*********************************************************************
Spring Break!

3/24:*********************************************************************
Project Proposal:
We've finished the project proposal.
Click here to view.

Design:
For development of our game we will be using the Dojo Game Engine. We will thus be coding in C++ using
Microsoft Visual Studio as our development IDE. As mentioned previously the game is broken into 3 main
components. The underlying physics engine, the move creation system and the fighting simulation / learning mode.



Development update:
Move and Fighting UIs: First iteration interfaces are ready for testing.
Physics/Graphics Engine: Very rough marionette engine test bed done and ready for use.
AI: We've outlined basic AI architecture.


3/17:*********************************************************************
Conceptual artwork update:
Player artwork:
Here's a few sketches of players for our game.




GUI artwork:
Here's a screenshot of what we hope our GUI will look like for our move editor.
You will be able to select limbs on a player and create moves.
The user will have the ability to replay moves and save as well as
associate the move with a voice command.


3/10:**********************************************************************

Project Weekly: This is the project weekly that we'll be writing our proposal on.
Title:
Kung Fu Tamagotchi
Tagline:
Mr Myagi Evolved
Genre:
RPG & Fighter.
Mechanics:
Tamagotchi meets Soul Calibur
Setting:
Medieval meets Futuristic
Target Audience:
“soccer mom ”, Japanese teenager
Goal:
Create the ultimate fighting machine.
Description:
You get to train a young budding fighter how to fight. You get to make your own,
original PHYSICS BASED MOVES. You get to pit your Kung Fu Tamagotchi
against your friend’s to show them who the real Mr. Myagi is.
It is innovative because...
It’s a physics based fighting simulation where your trainee learns from you and
from experience in fights. You get to make your own moves which can be modified
and perfected. There is also the possibility of having the trainee make up his/her
own moves.