We introduce Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human intervention. Voyager consists of three key components: 1) an automatic curriculum that maximizes exploration, 2) an ever-growing skill library of executable code for storing and retrieving complex behaviors, and 3) a new iterative prompting mechanism that incorporates environment feedback, execution err ...
This is a gym environment for RL agents to play Pokemon Gold.
Autonomous agents have made great strides in specialist domains like Atari games and Go. However, they typically learn tabula rasa in isolated environments with limited and manually conceived objectives, thus failing to generalize across a wide spectrum of tasks and capabilities. Inspired by how humans continually learn and adapt in the open world, we advocate a trinity of ingredients for building generalist agents: 1) an environment that supports a multitude of tasks and goals, 2) a large-scale ...
XR projects made in EECS 498-003
In this project, we implemented Wasserstein in Generative Adversarial Network (WGAN), as well as WGAN with gradient penalty (WGANGP). Wasserstein Generative Adversarial Networks (WGAN) was developed based on the Generative Adversarial Networks (GAN), which is a powerful generative model but still suffering from some defects. It modified the loss function of the original GAN, which made the training more stable and solved the mode collapse problem of the original GAN. The main breaking point of t ...
