Add AI players with configurable strategies by Copilot · Pull Request #67 · durangogt/aggravation

Copilot · 2026-02-11T05:25:29Z

Implements AI opponents to enable solo play and AI vs AI simulation. The existing game_engine.py architecture (get_valid_moves() + execute_move()) provided a clean interface for AI integration.

Implementation

AI Strategy System

Base AIPlayer class with choose_move(game, dice_roll) -> Optional[int] interface
Three concrete strategies:
- RandomStrategy (easy): Random selection from valid moves
- AggressiveStrategy (medium): Scores moves by forward progress + aggravation potential
- DefensiveStrategy (hard): Scores moves by safety + strategic positioning
Factory function create_ai_player(strategy_name, player_number, difficulty) for instantiation

Player Configuration

PlayerConfig class tracking player type (Human/AI) and strategy selection
PlayerSelectionScreen with pygame UI for interactive configuration
Toggle buttons for player type, dropdown for AI strategy selection

Game Modes

aggravation_ai.py launcher supporting three modes:
- Interactive: Player selection screen → game start
- Watch: --watch flag sets all players to AI
- Headless: --headless flag runs terminal-based simulation

Usage

# Programmatic usage
from ai_player import create_ai_player
from game_engine import AggravationGame

game = AggravationGame()
ai = create_ai_player('aggressive', player_number=1)

dice_roll = game.roll_dice()
move = ai.choose_move(game, dice_roll)  # Returns marble index or -1 for home

if move is not None:
    if move == -1:
        game.remove_from_home(1)
    else:
        game.execute_move(1, move, dice_roll)

# CLI usage
python aggravation_ai.py              # Interactive player selection
python aggravation_ai.py --watch      # All AI players
python aggravation_ai.py --headless   # Terminal simulation
python demo_ai.py                     # Strategy demonstration

Player Selection UI

Files Added

ai_player.py - Strategy implementations (410 lines)
player_selection.py - Configuration UI (347 lines)
aggravation_ai.py - Game launcher (245 lines)
test_ai_player.py - Test suite (19 tests, all passing)
demo_ai.py - Interactive demo (135 lines)

Limitations

GUI mode uses simplified text status display; full board visualization with AI moves not implemented
Human vs AI mixed mode requires additional game loop integration for human input

Original prompt

This section details on the original issue you should resolve

<issue_title>Add AI Players with Configurable StrategiesLabel</issue_title>
<issue_description>Issue 1

Title: Add AI Players with Configurable StrategiesLabel: featureBody:

Right now all 4 players are human-controlled. Adding AI opponents with selectable strategies (aggressive, defensive, shortcut-hunter, random) would make the game fun to play solo.

The game_engine.py architecture is already perfectly set up for this — get_valid_moves() + execute_move() is a clean AI interface.

Scope:

• Implement at least 3 AI strategy classes (random, aggressive, defensive)

• Add difficulty levels (easy/medium/hard)

• Support “watch AI vs AI” simulation mode

• Player selection screen to choose human vs AI for each seat</issue_description>

Comments on the Issue (you are @copilot in this section)

Fixes Add AI Players with Configurable StrategiesLabel #66

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.

Co-authored-by: durangogt <10979447+durangogt@users.noreply.github.com>

…dling Co-authored-by: durangogt <10979447+durangogt@users.noreply.github.com>

Co-authored-by: durangogt <10979447+durangogt@users.noreply.github.com>

Copilot

Pull request overview

This pull request adds AI player capabilities to the Aggravation board game, enabling solo play and AI vs AI simulation. The implementation leverages the existing game engine's get_valid_moves() and execute_move() interface to provide three distinct AI strategies with different difficulty levels.

Changes:

Adds three AI strategies (Random/Easy, Aggressive/Medium, Defensive/Hard) with distinct decision-making algorithms
Implements interactive player selection screen for configuring Human vs AI players
Provides three game modes: interactive player selection, watch AI vs AI, and headless simulation
Includes comprehensive test suite with 19 tests covering all strategies and integration scenarios
Updates documentation with detailed usage examples and strategy descriptions

Reviewed changes

Copilot reviewed 7 out of 8 changed files in this pull request and generated 7 comments.

Show a summary per file

File	Description
ai_player.py	Implements base AIPlayer class and three concrete strategies (Random, Aggressive, Defensive) with move selection logic
player_selection.py	Provides pygame-based UI for interactive player type and strategy configuration
aggravation_ai.py	Main launcher supporting interactive, watch, and headless game modes with AI integration
test_ai_player.py	Comprehensive test suite with 19 tests covering factory creation, strategy behavior, and integration
demo_ai.py	Interactive demonstration script showing AI decision-making and move execution
README.md	Documentation updates with AI feature description, usage examples, and strategy explanations
AI_IMPLEMENTATION.md	Detailed implementation summary documenting architecture, requirements, and limitations
screenshots/player_selection.png	Screenshot of the player selection UI (binary file)

Copilot · 2026-02-22T01:36:40Z

+    def _calculate_safety_score(self, game: AggravationGame, position: Tuple[int, int]) -> float:
+        """Calculate how safe a position is (higher = safer)."""
+        # Positions in final home are completely safe
+        if position in PLAYER_FINAL_HOMES[self.player_number]:
+            return 100
+
+        # Positions in home stretch are safer
+        if position in PLAYER_HOME_STRETCHES[self.player_number]:
+            return 50
+
+        # Check if any opponent could land on this position
+        danger_score = 30  # Base safety score
+
+        # Check all opponent marbles to see if they could reach this position
+        for opp_player in range(1, 5):
+            if opp_player == self.player_number:
+                continue
+
+            opp_data = game._get_player_data(opp_player)
+            opp_marbles = opp_data['marbles']
+
+            for opp_marble in opp_marbles:
+                if opp_marble is None or opp_marble == (None, None):
+                    continue
+
+                # Check if opponent could reach this position with any dice roll (1-6)
+                for dice in range(1, 7):
+                    test_pos = opp_marble
+                    for _ in range(dice):
+                        try:
+                            test_pos = game.get_next_position(test_pos[0], test_pos[1])
+                        except (AssertionError, IndexError):
+                            # get_next_position uses assertions for validation
+                            # TODO: game_engine should raise specific exceptions instead
+                            break
+                        if test_pos is None:
+                            break
+
+                    if test_pos == position:
+                        danger_score -= 10  # Reduce safety score
+                        break  # No need to check other dice rolls for this marble
+
+        return max(0, danger_score)


The _calculate_safety_score method has O(n×m×6×d) complexity where n=number of opponents, m=marbles per player, d=max dice value. For each valid move being evaluated, this checks if any opponent could reach the position with any dice roll (1-6). While functional, this could be slow when evaluating multiple moves. Consider optimizing if performance becomes an issue, perhaps by caching threat calculations or using a simpler heuristic.

Copilot · 2026-02-22T01:36:40Z

+"""
+
+import sys
+import os


The os module is imported but never used in this file. Consider removing this unused import.

Suggested change

import os

Copilot · 2026-02-22T01:36:41Z

+import sys
+import os
+import random
+import time


The time module is imported but never used in this file. The code uses pygame.time.wait() instead. Consider removing this unused import.

Suggested change

import time

Copilot · 2026-02-22T01:36:41Z

+
+import sys
+import os
+import random


The random module is imported but never used in this file. Consider removing this unused import.

Suggested change

import random

Copilot · 2026-02-22T01:36:41Z

+                result = game.execute_move(current_player, move, dice_roll)
+                if result['success']:
+                    print(f"  Moved marble {move} from {result['old_position']} to {result['new_position']}")
+                    if result.get('aggravation'):


The key name in the result dictionary doesn't match the game engine's return value. The execute_move function in game_engine.py returns 'aggravated_opponent' as the key (see game_engine.py:514, 563), but this code checks for 'aggravation'. This will always be falsy, preventing the aggravation message from being displayed.

Suggested change

if result.get('aggravation'):

if result.get('aggravated_opponent'):

Copilot · 2026-02-22T01:36:41Z

+                    result = game.execute_move(current_player, move, dice_roll)
+                    if result['success']:
+                        msg = f"Player {current_player}: Moved marble {move}"
+                        if result.get('aggravation'):


The key name in the result dictionary doesn't match the game engine's return value. The execute_move function in game_engine.py returns 'aggravated_opponent' as the key (see game_engine.py:514, 563), but this code checks for 'aggravation'. This will always be falsy, preventing the aggravation message from being displayed.

Suggested change

if result.get('aggravation'):

if result.get('aggravated_opponent'):

Copilot · 2026-02-22T01:36:42Z

+                print(f"  AI moved marble {move}")
+                print(f"  From: {result['old_position']}")
+                print(f"  To:   {result['new_position']}")
+                if result.get('aggravation'):


The key name in the result dictionary doesn't match the game engine's return value. The execute_move function in game_engine.py returns 'aggravated_opponent' as the key (see game_engine.py:514, 563), but this code checks for 'aggravation'. This will always be falsy, preventing the aggravation message from being displayed.

Suggested change

if result.get('aggravation'):

if result.get('aggravated_opponent'):

Initial plan

09a62fe

Copilot AI assigned Copilot and durangogt Feb 11, 2026

Copilot started work on behalf of durangogt February 11, 2026 05:25 View session

Copilot AI and others added 5 commits February 11, 2026 05:28

Add AI player strategies (Random, Aggressive, Defensive)

6151f93

Co-authored-by: durangogt <10979447+durangogt@users.noreply.github.com>

Add player selection UI and AI game launcher

7ff3c13

Co-authored-by: durangogt <10979447+durangogt@users.noreply.github.com>

Add AI documentation and demo script

fcd0465

Co-authored-by: durangogt <10979447+durangogt@users.noreply.github.com>

Address code review feedback - add TODO comments and better error han…

4fba779

…dling Co-authored-by: durangogt <10979447+durangogt@users.noreply.github.com>

Add AI implementation summary documentation

b9741e3

Co-authored-by: durangogt <10979447+durangogt@users.noreply.github.com>

Copilot AI changed the title ~~[WIP] Add AI players with configurable strategies~~ Add AI players with configurable strategies Feb 11, 2026

Copilot AI requested a review from durangogt February 11, 2026 05:37

Copilot finished work on behalf of durangogt February 11, 2026 05:37

durangogt requested review from Copilot and removed request for durangogt February 22, 2026 01:31

Copilot started reviewing on behalf of durangogt February 22, 2026 01:32 View session

Copilot AI reviewed Feb 22, 2026

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Add AI players with configurable strategies#67

Add AI players with configurable strategies#67
durangogt with Copilot wants to merge 6 commits into
mainfrom
copilot/add-ai-players-strategies

Copilot AI commented Feb 11, 2026 •

edited

Loading

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Feb 22, 2026

Uh oh!

Copilot AI Feb 22, 2026

Uh oh!

Copilot AI Feb 22, 2026

Uh oh!

Copilot AI Feb 22, 2026

Uh oh!

Copilot AI Feb 22, 2026

Uh oh!

Copilot AI Feb 22, 2026

Uh oh!

Copilot AI Feb 22, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

	if result.get('aggravation'):
	if result.get('aggravated_opponent'):

Conversation

Copilot AI commented Feb 11, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Implementation

AI Strategy System

Player Configuration

Game Modes

Usage

Player Selection UI

Files Added

Limitations

Comments on the Issue (you are @copilot in this section)

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Feb 22, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 22, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 22, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 22, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 22, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 22, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 22, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Copilot AI commented Feb 11, 2026 •

edited

Loading