From 3d0a8662b386eae41252f935d646f549a1f5fde9 Mon Sep 17 00:00:00 2001 From: hubcity Date: Thu, 26 Mar 2020 00:46:13 -0400 Subject: [PATCH] #7246 - Fixing broken links (#7247) * #7246 - Fixing broken links * Apply suggestions from code review Co-authored-by: Richard Liaw --- doc/source/rllib-algorithms.rst | 2 +- doc/source/rllib-concepts.rst | 2 +- doc/source/rllib-env.rst | 4 ++-- doc/source/rllib-examples.rst | 6 +++--- doc/source/tune-searchalg.rst | 4 ++-- 5 files changed, 9 insertions(+), 9 deletions(-) diff --git a/doc/source/rllib-algorithms.rst b/doc/source/rllib-algorithms.rst index 804c979a9..89c42bff7 100644 --- a/doc/source/rllib-algorithms.rst +++ b/doc/source/rllib-algorithms.rst @@ -241,7 +241,7 @@ RLlib DQN is implemented using the SyncReplayOptimizer. The algorithm can be sca DQN architecture -Tuned examples: `PongDeterministic-v4 `__, `Rainbow configuration `__, `{BeamRider,Breakout,Qbert,SpaceInvaders}NoFrameskip-v4 `__, `with Dueling and Double-Q `__, `with Distributional DQN `__. +Tuned examples: `PongDeterministic-v4 `__, `Rainbow configuration `__, `{BeamRider,Breakout,Qbert,SpaceInvaders}NoFrameskip-v4 `__, `with Dueling and Double-Q `__, `with Distributional DQN `__. .. tip:: Consider using `Ape-X <#distributed-prioritized-experience-replay-ape-x>`__ for faster training with similar timestep efficiency. diff --git a/doc/source/rllib-concepts.rst b/doc/source/rllib-concepts.rst index a159a3e9b..57a272145 100644 --- a/doc/source/rllib-concepts.rst +++ b/doc/source/rllib-concepts.rst @@ -275,7 +275,7 @@ Now let's take a look at the ``update_kl`` function. This is used to adaptively # multi-agent trainer.workers.local_worker().foreach_trainable_policy(update) -The ``update_kl`` method on the policy is defined in `PPOTFPolicy `__ via the ``KLCoeffMixin``, along with several other advanced features. Let's look at each new feature used by the policy: +The ``update_kl`` method on the policy is defined in `PPOTFPolicy `__ via the ``KLCoeffMixin``, along with several other advanced features. Let's look at each new feature used by the policy: .. code-block:: python diff --git a/doc/source/rllib-env.rst b/doc/source/rllib-env.rst index c7bbd4dd6..69e38cc5e 100644 --- a/doc/source/rllib-env.rst +++ b/doc/source/rllib-env.rst @@ -165,7 +165,7 @@ If all the agents will be using the same algorithm class to train, then you can RLlib will create three distinct policies and route agent decisions to its bound policy. When an agent first appears in the env, ``policy_mapping_fn`` will be called to determine which policy it is bound to. RLlib reports separate training statistics for each policy in the return from ``train()``, along with the combined reward. -Here is a simple `example training script `__ in which you can vary the number of agents and policies in the environment. For how to use multiple training methods at once (here DQN and PPO), see the `two-trainer example `__. Metrics are reported for each policy separately, for example: +Here is a simple `example training script `__ in which you can vary the number of agents and policies in the environment. For how to use multiple training methods at once (here DQN and PPO), see the `two-trainer example `__. Metrics are reported for each policy separately, for example: .. code-block:: bash :emphasize-lines: 6,14,22 @@ -223,7 +223,7 @@ RLlib will create each policy's model in a separate ``tf.variable_scope``. Howev auxiliary_name_scope=False): -There is a full example of this in the `example training script `__. +There is a full example of this in the `example training script `__. Implementing a Centralized Critic ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/doc/source/rllib-examples.rst b/doc/source/rllib-examples.rst index c4a4762e1..832183fd1 100644 --- a/doc/source/rllib-examples.rst +++ b/doc/source/rllib-examples.rst @@ -71,11 +71,11 @@ Multi-Agent and Hierarchical Example of customizing PPO to leverage a centralized value function. - `Centralized critic in the env `__: A simpler method of implementing a centralized critic by augmentating agent observations with global information. -- `Hand-coded policy `__: +- `Hand-coded policy `__: Example of running a custom hand-coded policy alongside trainable policies. -- `Weight sharing between policies `__: +- `Weight sharing between policies `__: Example of how to define weight-sharing layers between two different policies. -- `Multiple trainers `__: +- `Multiple trainers `__: Example of alternating training between two DQN and PPO trainers. - `Hierarchical training `__: Example of hierarchical training using the multi-agent API. diff --git a/doc/source/tune-searchalg.rst b/doc/source/tune-searchalg.rst index 3dae5b8b0..25f0d8698 100644 --- a/doc/source/tune-searchalg.rst +++ b/doc/source/tune-searchalg.rst @@ -149,7 +149,7 @@ In order to use this search algorithm, you will need to install Nevergrad via th Keep in mind that ``nevergrad`` is a Python 3.6+ library. -This algorithm requires using an optimizer provided by ``nevergrad``, of which there are many options. A good rundown can be found on their README's `Optimization `__ section. You can use ``NevergradSearch`` like follows: +This algorithm requires using an optimizer provided by ``nevergrad``, of which there are many options. A good rundown can be found on their README's `Optimization `__ section. You can use ``NevergradSearch`` like follows: .. code-block:: python @@ -172,7 +172,7 @@ In order to use this search algorithm, you will need to install Scikit-Optimize $ pip install scikit-optimize -This algorithm requires using the `Scikit-Optimize ask and tell interface `__. This interface requires using the `Optimizer `__ provided by Scikit-Optimize. You can use SkOptSearch like follows: +This algorithm requires using the `Scikit-Optimize ask and tell interface `__. This interface requires using the `Optimizer `__ provided by Scikit-Optimize. You can use SkOptSearch like follows: .. code-block:: python