Mini-Contest 2: Multi-Agent Adversarial Pacman (due 3/11 11:59pm)
Table of Contents
Enough of defense,
Onto enemy terrain.
Capture all their food!
This minicontest involves a multi-player capture-the-flag variant of Pacman, where agents control both Pacman and
ghosts in coordinated team-based strategies. Your team will try to eat the food on the far side of the map, while
defending the food on your home side. The contest code is available as a zip archive (
You may choose to work alone or with one partner. There is room to bring your own unique ideas, and there is no single set solution. Much looking forward to seeing what you come up with!
Extra credit points are earned on top of the 25 points available in P2. E.g. if you earn 1 point of EC through the mini-contest and had a 25/25 on P2, then you'll have 26/25 on P2.
Your agent will be tested on Gradescope against the baseline and a few staff agents on several selected maps in
- 0.5 points for over 51% winning rate against the provided baseline agent in
- 0.5 points for over 51% winning rate against "Staff Agent 1".
- 0.5 points for over 51% winning rate against "Staff Agent 2".
- 0.5 points for over 51% winning rate against "Staff Agent 3".
Students that perform well in the final leaderboard, ranked by "final score" metric, will receive the following:
- 1st place: 2 points
- 2nd and 3rd place: 1.5 points
- 4th to 10th place: 1 point
The primary change between the first and second contests is that now it is an adversarial game, involving two teams competing against each other. Your team will try to eat the food on the far side of the map, while defending the food on your home side.
Your agents are in the form of ghosts on your home side and Pacman on your opponent's side. Also, you are now able to eat your opponent when you are a ghost. If Pacman is eaten by a ghost before reaching his own side of the board, he will explode into a cloud of food dots that will be deposited back onto the board.
Note that the contest framework, provided in
minicontest2.zip, has changed slightly from Contest 1. The functions and interfaces
are nearly the same, but maps now include power capsules and you can eat your opponents.
External libraries: in this contest, you are allowed to use numpy as a dependency.
|Files you'll edit:|
||What will be submitted to Gradescope. Contains all of the code needed for your agent.|
|Files you might want to look at:|
||The main file that runs games locally. This file also describes the new capture the flag GameState type and rules.|
||Specification and helper methods for capture agents.|
||Example code that defines two very basic reflex agents, to help you get started.|
|Supporting Files (Do not Modify):|
||The logic behind how the Pacman world works. This file describes several supporting types like AgentState, Agent, Direction, and Grid.|
||Useful data structures for implementing search algorithms.|
||Computes shortest paths between all maze positions.|
||Graphics for Pacman|
||Support for Pacman graphics|
||ASCII graphics for Pacman|
||Keyboard interfaces to control Pacman|
||Code for reading layout files and storing their contents|
Files to Edit and Submit: You will fill and submit
Academic Dishonesty: We will be checking your code against other submissions in the class for logical redundancy. If you copy someone else's code and submit it with minor changes, we will know. These cheat detectors are quite hard to fool, so please don't try. We trust you all to submit your own work only; please don't let us down. If you do, we will pursue the strongest consequences available to us.
Getting Help: You are not alone! If you find yourself stuck on something, contact the course staff for help. Office hours, section, and the discussion forum are there for your support; please use them. If you can't make our office hours, let us know and we will schedule more. We want these contests to be rewarding and instructional, not frustrating and demoralizing. But, we don't know when or how to help unless you ask.
Discussion: Please be careful not to post spoilers.
The Pacman map is now divided into two halves: blue (right) and red (left). Red agents (which all have even indices) must defend the red food while trying to eat the blue food. When on the red side, a red agent is a ghost. When crossing into enemy territory, the agent becomes a Pacman.
There are a variety of layout in the
As a Pacman eats food dots, those food dots are stored up inside of that Pacman and removed from the board. When a Pacman returns to his side of the board, he "deposits" the food dots he is carrying, earning one point per food pellet delivered. Red team scores are positive, while Blue team scores are negative.
If Pacman gets eaten by a ghost before reaching his own side of the board, he will explode into a cloud of food dots that will be deposited back onto the board.
If Pacman eats a power capsule, agents on the opposing team become "scared" for the next 40 moves, or until they are eaten and respawn, whichever comes sooner. Agents that are "scared" are susceptible while in the form of ghosts (i.e. while on their own team's side) to being eaten by Pacman. Specifically, if Pacman collides with a "scared" ghost, Pacman is unaffected and the ghost respawns at its starting position (no longer in the "scared" state).
Each agent can see the entire state of the game, such as food pellet locations, all pacman locations, all ghost locations, etc. See the GameState section for more details.
In this adversarial game, a team wins when they return all but two of the opponents' dots. Games are also limited to 1200 agent moves (moves can be unequally shared depending on different speeds - faster agents get more moves). If this move limit is reached, whichever team has returned the most food wins.
If the score is zero (i.e., tied) this is recorded as a tie game.
Each agent has 1 second to return each action. Each move which does not return within one second will incur a
warning. After three warnings, or any single move taking more than 3 seconds, the game is forfeit. There will be an
initial start-up allowance of 15 seconds (use the
An agent now has the more complex job of trading off offense versus defense and effectively functioning as both a ghost and a Pacman in a team setting. The added time limit of computation introduces new challenges.
To kickstart your agent design, we have provided you with a team of two baseline agents, defined in
They are quite bad. The
OffensiveReflexAgent simply moves toward the closest food on the opposing side.
DefensiveReflexAgent wanders around on its own side and tries to chase down invaders it happens to
You should include your agents in a file of the same format as
myTeam.py. Your agents must be
completely contained in this one file.
capture.py should look familiar, but contains new methods like
which gets a grid of food on the red side (note that the grid is the size of the board, but is only true for cells
on the red side with food). Also, note that you can list a team's indices with
test membership with
To facilitate agent development, we provide code in
distanceCalculator.py to supply shortest path maze
To get started designing your own agent, we recommend subclassing the
CaptureAgent class. This
provides access to several convenience methods. Some useful methods are:
Returns the food you're meant to eat. This is in the form of a matrix where
if there is food you can eat (based on your team) in that square.
Returns the food you're meant to protect (i.e., that your opponent is supposed to eat). This
is in the form of a matrix where
m[x][y]=True if there is food at
(x,y) that your
opponent can eat.
Returns agent indices of your opponents. This is the list of the numbers of the agents (e.g.,
red might be
Returns agent indices of your team. This is the list of the numbers of the agents (e.g., blue
Returns how much you are beating the other team by in the form of a number that is the difference between your score and the opponents score. This number is negative if you're losing.
Returns the distance between two points; These are calculated using the provided distancer
distancer.getMazeDistances() has been called, then maze distances are available.
Otherwise, this just returns Manhattan distance.
GameState object corresponding to the last state this agent saw (the
observed state of the game last time this agent moved).
GameState object corresponding this agent's current observation (the
observed state of the game).
Draws a colored box on each of the cells you specify. If clear is
clear all old drawings before drawing on the specified cells. This is useful for debugging the locations that your
code works with. color: list of RGB values between 0 and 1 (i.e.
[1,0,0] for red) cells: list of game
positions to draw on (i.e.
You are free to design any agent you want. However, you will need to respect the provided APIs if you want to participate in the contest. Agents which compute during the opponent's turn will be disqualified. In particular, any form of multi-threading is disallowed, because we have found it very hard to ensure that no computation takes place on the opponent's turn.
Please respect the APIs and keep all of your implementation within
By default, you can run a game with the simple
baselineTeam that the staff has provided:
A wealth of options are available to you:
python capture.py --help
There are four slots for agents, where agents 0 and 2 are always on the red team, and 1 and 3 are on the blue team.
Agents are created by agent factories (one for Red, one for Blue). See the section on designing agents for a
description of the agents invoked above. The only team that we provide is the
baselineTeam. It is
chosen by default as both the red and blue team, but as an example of how to choose teams:
python capture.py -r baselineTeam -b baselineTeam
which specifies that the red team
-r and the blue team
-b are both created from
To control one of the four agents with the keyboard, pass the appropriate option:
python capture.py --keys0
The arrow keys control your character, which will change from ghost to Pacman when crossing the center line.
By default, all games are run on the
defaultcapture layout. To test your agent on other layouts, use
-l option. In particular, you can generate random layouts by specifying
-l RANDOM13 will use a map randomly generated with seed 13.
You can record local games using the
--record option, which will write the game history to a file
named by the time the game was played. You can replay these histories using the
--replay option and
specifying the file to replay.