eloialonso/diamond

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2118 stars · 168 forks observed · 2026-10-13

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

DIAMOND is a Python implementation of a reinforcement learning agent trained entirely inside a diffusion-based world model, presented as a NeurIPS 2024 Spotlight paper. It includes pretrained playable world models for Atari games and a CS:GO world model that acts as an interactive neural game engine.

Use cases

• train RL agents inside a learned diffusion world model
• play Atari games generated by a neural world model
• run an interactive neural game engine simulating CS:GO
• reproduce the DIAMOND Atari 100k benchmark results
• research diffusion models for environment dynamics modeling
• experiment with world model training pipelines in PyTorch

When to choose

• you need sample-efficient RL training in an imagined environment
• you want to study or extend diffusion-based world models
• you want a playable neural game engine demo
• you need a strong baseline for world-model RL research

When to avoid

• you need a production game engine or real-time commercial performance
• you lack a GPU or don't want heavy PyTorch training workloads
• you need a general-purpose RL library rather than a research codebase
• you cannot license Atari ROMs for your use

Facets

library · maturity active

reinforcement-learning machine-learning deep-learning simulation game reinforcement-learning artificial-intelligence deep-learning gaming-tools python cross-platform diffusion-models world-models neural-game-engine atari csgo research-code neurips-2024 research gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="eloialonso/diamond")