Ryan Julian

icon indicating a website link ryanjulian.me

icon company USC, @rlworkgroup, @google icon location Los Angeles, CA icon location Roboticist and PhD student at USC studying the intersection of robotics and machine learning. Formerly at Berkeley, Leap Motion, and Google X.

Results 39 issues of Ryan Julian

Move garage.tf.samplers.worker to garage.sampler

This is a good implementation of conditional behavior, but it makes more sense for it to live with the rest of the codebase.

API

Add comprehensive documentation

This is an umbrella issue, as this will be a large project. Overall outline format inspired by https://documentation.divio.com/ * [x] Installation * [x] Getting Started * [ ] Usage Guide...

documentation

Docs page "Reference Guide -> Framework-specific notes -> PyTorch"

documentation

Docs page "Reference Guide -> Framework-specific notes -> TensorFlow"

documentation

Docs page "Reference Guide -> Framework-specific notes -> NumPy"

documentation

Docs page "Reference Guide -> Core Concepts -> Snapshotter"

documentation

Docs page "Reference Guide -> Core Concepts -> RLAlgorithm/MetaRLAlgorithm"

documentation

Docs page "RL Resources"

Should provide pointers to intro resources for learning about RL before using garage * openai spinningup * Berkeley DeepRL course * David Silver course * Others?

documentation

Document environment pickling better in Tutorials -> Implementing a new Environment

This is a very frequent question. We should provide an example which satisfies 90% of use cases (e.g. gym.utils.EzPickle or equivalent.

documentation

Distribute on pip