| dreamerv3 | Mastering Diverse Domains through World Models | |
| daydreamer* | DayDreamer: World Models for Physical Robot Learning | |
| director* | Deep Hierarchical Planning from Pixels | |
| dreamerv2* | Mastering Atari with Discrete World Models | |
| dreamer* | Dream to Control: Learning Behaviors by Latent Imagination | |
| planet* | Learning Latent Dynamics for Planning from Pixels | |
| batch-ppo* | Efficient Batched Reinforcement Learning in TensorFlow |
| granular | Fast format and loader for datasets | |
| portal | Fast and reliable distributed systems in Python | |
| elements | Building blocks for productive research | |
| ninjax | General Modules for JAX | |
| flexbuild | Simple Python build backend for large codebases | |
| handout* | Turn Python scripts into handouts with Markdown and figures |
| crafter | Benchmarking the Spectrum of Agent Capabilities | |
| diamond_env | Standardized Minecraft Diamond task for reinforcement learning |
* Archived