A Simplified Pytorch Version of the Dreamer Algorithm
Autonomous FPV drone control with pure vision input
UrbanWorldModel, UrbanSim WM is a DreamerV3-style world model for simulating city-scale air quality, energy, and mobility under policy interventions. It provides a Dockerized FastAPI + Next.js app with WAQI ETL integration, real-time PM2.5 inference, interactive charts, and a training pipeline in PyTorch.
Extending DreamerV3 for robotic application and better Morphologieawareness by implementing a FFKSM
We explore the power of learning within a latent world model vs standard reinforcement learning baselines. We implement DreamerV3 as our world model in the environment of Flappy Birds.
A minimal, from-scratch PyTorch implementation of the DreamerV3 agent applied to autonomous vehicular control (CarRacing-v3). Demonstrates categorical latent physics, pixel-to-latent compression, and continuous environment control.
To associate your repository with the dreamer-v3 topic, visit your repo's landing page and select "manage topics."