Play and train agents in an interactive pyramid game
Play a game where a dog catches sticks
Play an interactive soccer game called SoccerTwos
Control a simulated vehicle using keyboard
Play the Dodge game
Launch an interactive Unity game in your browser
https://huggingface.co/spaces/VIDraft/mouse-webgen
Play KexFarm Unity game
Explore a pyramid-solving game with AI
Play with a stick-catching dog 🐶
Run and customize ML agents in a simulation
Start Godot Engine for game development directly in your browser
Play a web-based Unity game
ML Agents Pyramids is an interactive Game AI application designed for training and playing with intelligent agents in a pyramid-based game environment. It provides a unique space for experimenting with AI decision-making and learning behaviors in a structured, goal-oriented setting. Whether you're a researcher, developer, or casual gamer, ML Agents Pyramids offers a fun and educational experience for exploring AI capabilities.
• Interactive Game Environment: Engage with a pyramid-shaped board where agents can move and make decisions.
• Real-Time Feedback: Observe agent behavior and outcomes as they navigate the pyramid.
• Customizable Scenarios: Adjust game rules, agent goals, and pyramid configurations to test various AI strategies.
• Multiple Training Modes: Choose between supervised learning, reinforcement learning, or imitation learning approaches.
• Visualization Tools: Track agent performance, learning curves, and decision-making processes in real time.
What type of AI models can I train with ML Agents Pyramids?
You can train models using reinforcement learning, imitation learning, or supervised learning methods, depending on your goals.
Do I need prior knowledge of machine learning to use ML Agents Pyramids?
While some understanding of AI concepts is helpful, the tool is designed to be accessible to both beginners and experts.
Can I customize the game rules or pyramid structure?
Yes, ML Agents Pyramids allows you to modify game rules and adjust pyramid configurations to suit your experimental needs.