From 670cb6374e215363e2911e73da12c4592cb1b444 Mon Sep 17 00:00:00 2001 From: Shital Shah Date: Mon, 2 Dec 2019 22:19:01 -0800 Subject: [PATCH] Doc enhancement: use build.sh for ray, clarification on how rllib selects VisionNetwork, note on setup-dev.py for rllib. (#6092) --- doc/source/development.rst | 4 ++-- doc/source/rllib-dev.rst | 2 +- doc/source/rllib-models.rst | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/doc/source/development.rst b/doc/source/development.rst index 4346e5657..6b3ffdf75 100644 --- a/doc/source/development.rst +++ b/doc/source/development.rst @@ -23,14 +23,14 @@ you can try adding ``--user``. You may also need to run something like ``sudo chown -R $USER /home/ubuntu/anaconda3`` (substituting in the appropriate path). -If you make changes to the C++ files, you will need to recompile them. +If you make changes to the C++ or Python files, you will need to run the build so C++ code is recompiled and/or Python files are redeployed in `ray/python`. However, you do not need to rerun ``pip install -e .``. Instead, you can recompile much more quickly by doing .. code-block:: shell cd ray - bazel build //:ray_pkg + bash build.sh This command is not enough to recompile all C++ unit tests. To do so, see `Testing locally`_. diff --git a/doc/source/rllib-dev.rst b/doc/source/rllib-dev.rst index d219df644..18e18a739 100644 --- a/doc/source/rllib-dev.rst +++ b/doc/source/rllib-dev.rst @@ -4,7 +4,7 @@ RLlib Development Development Install ------------------- -You can develop RLlib locally without needing to compile Ray by using the `setup-dev.py `__ script. This sets up links between the ``rllib`` dir in your git repo and the one bundled with the ``ray`` package. When using this script, make sure that your git branch is in sync with the installed Ray binaries (i.e., you are up-to-date on `master `__ and have the latest `wheel `__ installed.) +You can develop RLlib locally without needing to compile Ray by using the `setup-dev.py `__ script. This sets up links between the ``rllib`` dir in your git repo and the one bundled with the ``ray`` package. However if you have installed ray from source using [these instructions](https://ray.readthedocs.io/en/latest/installation.html) then do not this as these steps should have already created this symlink. When using this script, make sure that your git branch is in sync with the installed Ray binaries (i.e., you are up-to-date on `master `__ and have the latest `wheel `__ installed.) API Stability ------------- diff --git a/doc/source/rllib-models.rst b/doc/source/rllib-models.rst index 0c16d2b0d..4079294c4 100644 --- a/doc/source/rllib-models.rst +++ b/doc/source/rllib-models.rst @@ -14,7 +14,7 @@ Default Behaviours Built-in Models and Preprocessors ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -RLlib picks default models based on a simple heuristic: a `vision network `__ for image observations, and a `fully connected network `__ for everything else. These models can be configured via the ``model`` config key, documented in the model `catalog `__. Note that you'll probably have to configure ``conv_filters`` if your environment observations have custom sizes, e.g., ``"model": {"dim": 42, "conv_filters": [[16, [4, 4], 2], [32, [4, 4], 2], [512, [11, 11], 1]]}`` for 42x42 observations. +RLlib picks default models based on a simple heuristic: a `vision network `__ for observations that have shape of length larger than 2 (for example, (84 x 84 x 3)), and a `fully connected network `__ for everything else. These models can be configured via the ``model`` config key, documented in the model `catalog `__. Note that you'll probably have to configure ``conv_filters`` if your environment observations have custom sizes, e.g., ``"model": {"dim": 42, "conv_filters": [[16, [4, 4], 2], [32, [4, 4], 2], [512, [11, 11], 1]]}`` for 42x42 observations. In addition, if you set ``"model": {"use_lstm": true}``, then the model output will be further processed by a `LSTM cell `__. More generally, RLlib supports the use of recurrent models for its policy gradient algorithms (A3C, PPO, PG, IMPALA), and RNN support is built into its policy evaluation utilities.