Danijar Hafner's Projects
Enhances the Ace Editor with real time collaboration user experience.
Efficient Batched Reinforcement Learning in TensorFlow
Official Open Asset Import Library Repository. Loads 40+ 3D file formats into one unified and clean data structure.
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
Chrome plugin to select which bookmarks folder to show as the bookmarks bar
Visual reinforcement learning benchmark for controllability
Bullet Physics 3.x AND Bullet 2 official repository with GPU rigid body pipeline
Save file writes into multiple chunks
Extend pathlib to GCS, S3, HDFS via TensorFlow's GFile
Collaborative Extensions for CodeMirror
Collaborative code editor using Ace Editor, Code-Mirror, and ShareDB
Data-oriented voxel game engine
Recurrent neural network implementation targeted towards evaluating new topologies
simple game running in the console
Programming assignments for the TU Munich Computer Vision course
Programming assignments for the Stanford Machine Learning course by Andrew Ng
Partially-observed visual reinforcement learning domain
Benchmarking the Spectrum of Agent Capabilities
Docker containers of baseline agents for the Crafter environment
DayDreamer: World Models for Physical Robot Learning
Load and validate YAML definitions against a schema
common css and js designs for reuse
Standardized Minecraft Diamond Environment for Reinforcement Learning
Deep Hierarchical Planning from Pixels
My Linux and Mac configuration
Dream to Control: Learning Behaviors by Latent Imagination