3d-environment

DeliveryGym is a 3D reinforcement learning environment for long-horizon embodied agent planning with adaptive curriculum, demonstrating performance improvements through RL.

The paper introduces MineAmongUs, a 3D multimodal Among Us environment, and the ARIA harness to study deception in VLM agents, finding that non-verbal actions are key to successful deception in social interactions.

UrbanGround evaluates whether multimodal language model agents can sustain reliable navigation and spatial reasoning in a realistic 3D city replica, revealing that local perceptual skills fail to compose into extended goal-directed behavior.

A CLI tool that transforms a single image into a fully meshed 3D environment with objects, ambient sound, and physics SFX in under five minutes by leveraging Claude skills, World Labs, and FAL models.