MultiAgentPacman is an educational Python framework that provides a ready-made Pacman environment for developing and testing various multi-agent AI algorithms. It includes built-in implementations of reflex agents, minimax, expectimax, alpha-beta pruning, and customizable agent templates, along with visualization and performance evaluation tools.
Promote this Tool
Update this Tool
MultiAgentPacman
MultiAgentPacman is an educational Python framework that provides a ready-made Pacman environment for developing and testing various multi-agent AI algorithms. It includes built-in implementations of reflex agents, minimax, expectimax, alpha-beta pruning, and customizable agent templates, along with visualization and performance evaluation tools.
Ads
What is MultiAgentPacman?
MultiAgentPacman offers a Python-based game environment where users can implement, visualize, and benchmark multiple AI agents in the Pacman domain. It supports adversarial search algorithms like minimax, expectimax, alpha-beta pruning, as well as custom reinforcement learning or heuristic-based agents. The framework includes a simple GUI, command-line controls, and utilities to log game statistics and compare agent performance under competitive or cooperative scenarios.
Who will use MultiAgentPacman?
- AI students and educators
- Reinforcement learning researchers
- Game AI developers
- Academic instructors
- AI algorithm enthusiasts
How to use the MultiAgentPacman?
- Step1: Clone the repository via git clone https://github.com/TejasNaikk/MultiAgentPacman.git
- Step2: Install Python 3.x and required dependencies (e.g., pygame) with pip install -r requirements.txt
- Step3: Run sample games using python pacman.py -p ReflexAgent or python pacman.py -p MinimaxAgent
- Step4: Create a custom agent by subclassing the Agent class in multiAgents.py
- Step5: Launch your agent with python pacman.py -p YourAgentName -l mediumMaze -q
- Step6: Use provided evaluation scripts to log wins, scores, and compare across multiple runs
Platform
- Linux
- Mac
- Windows
MultiAgentPacman's Core Features & Benefits
The Core Features
- Python-based Pacman game environment
- Multiple built-in agents: Reflex, Minimax, Expectimax, Alpha-Beta
- Custom agent API for heuristic and RL algorithms
- Real-time GUI visualization
- Command-line controls and logging utilities
- Performance evaluation and statistics
The Benefits
- Accelerates AI agent prototyping
- Teaches core adversarial and multi-agent concepts
- Facilitates reproducible benchmarking
- Open-source and highly extensible
- Interactive visualization of agent behaviors
MultiAgentPacman's Main Use Cases & Applications
- University AI course assignments and labs
- Benchmarking adversarial search algorithms
- Testing multi-agent reinforcement learning strategies
- Research in cooperative and competitive AI
- Game AI prototyping and demonstrations
FAQs of MultiAgentPacman
MultiAgentPacman Company Information
- TejasNaikk
MultiAgentPacman Reviews
5/5
MultiAgentPacman's Main Competitors and alternatives?
Berkeley CS188 Pacman Projects
OpenAI Gym Pacman environments
PettingZoo multi-agent Pacman
PyGame Learning Environment (PLE)
gym-pacman
You may also like:
Run coding agents in a persistent cloud workspace with shared files, previews, team context, and no local setup required.
Diagrid keeps AI agent workflows running through crashes, preserves state, and cryptographically proves every completed execution step.
Run coding agents locally with swappable models, tools, sandboxes, and session logs through a TypeScript plugin runtime.
Loopa is an AI agent platform that automates research, content creation, analysis, and workflow execution.
An autonomous AI agent that executes long tasks across apps, websites, and cloud computers end to end.
Hosted OpenClaw agent: one-click deploy, 500+ models, secure infrastructure, and automated agent management for teams and developers.
Enterprise-ready agent runtime that unifies Discord, web, and terminal with secure RAG, memory, and tool execution.
OpenClaw is an open-source, locally-run personal AI assistant that automates tasks via chat apps and plugins.
Managed Openclaw workspace to deploy local-first AI agents, hire AI staff, and join the Moltbook ecosystem.
CoTester is an enterprise-grade AI testing agent that reliably generates, runs, and self-heals automated tests.
Conversational AI assistant automating research, browser tasks, web scraping, and file management through natural language.
Gobii lets teams create 24/7 autonomous digital workers to automate web research and routine tasks.
AI design agent automates workflow creating images, videos, 3D models up to 10x faster.
SJinn is an AI-powered agent creating image, video, audio, and 3D content from descriptions.
Eigent is an open-source AI workforce platform managing complex workflows via multi-agent collaboration.
NVIDIA Omniverse Audio2Face transforms 3D character animations with AI-driven facial and emotional expressions.