Organize algos and title case all pages (#2164)

* Alphabetize algos and title case all pages * Alphabetize algos and title case all pages * Update title case
rlworkgroup · Oct 30, 2020 · 3b3ad04 · 3b3ad04
1 parent e8ffa13
commit 3b3ad04
Show file tree

Hide file tree

Showing 21 changed files with 36 additions and 36 deletions.
diff --git a/docs/index.md b/docs/index.md
@@ -49,21 +49,21 @@ and how to implement new MDPs and new algorithms.
    :maxdepth: 2
    :caption: Algorithms and Methods
 
-   user/algo_bc
-   user/algo_erwr
-   user/algo_trpo
-   user/algo_mttrpo
-   user/algo_sac
-   user/algo_mtsac
-   user/algo_pearl
-   user/algo_rl2
-   user/algo_ppo
-   user/algo_maml
-   user/algo_mtppo
-   user/algo_vpg
-   user/algo_td3
-   user/algo_ddpg
-   user/algo_cem
+   BC <user/algo_bc>
+   CEM <user/algo_cem>
+   DDPG <user/algo_ddpg>
+   ERWR <user/algo_erwr>
+   MAML <user/algo_maml>
+   MT-PPO <user/algo_mtppo>
+   MT-SAC <user/algo_mtsac>
+   MT-TRPO <user/algo_mttrpo>
+   PEARL <user/algo_pearl>
+   PPO <user/algo_ppo>
+   RL2 <user/algo_rl2>
+   SAC <user/algo_sac>
+   TD3 <user/algo_td3>
+   TRPO <user/algo_trpo>
+   REINFORCE <user/algo_vpg>
 
 .. toctree::
    :maxdepth: 2

diff --git a/docs/user/algo_bc.md b/docs/user/algo_bc.md
@@ -1,4 +1,4 @@
-# Behavioral Cloning
+# Behavioral Cloning (BC)
 
 ```eval_rst
 +-------------------+--------------------------------------------------------------------------------------------------------------+

diff --git a/docs/user/algo_cem.md b/docs/user/algo_cem.md
@@ -1,4 +1,4 @@
-# Cross Entropy Method
+# Cross Entropy Method (CEM)
 
 ```eval_rst
 +-------------------+--------------------------------------------------------------------------------------------------------------------------------------------------+

diff --git a/docs/user/algo_ddpg.md b/docs/user/algo_ddpg.md
@@ -1,4 +1,4 @@
-# DDPG
+# Deep Deterministic Policy Gradient (DDPG)
 
 ```eval_rst
 +-------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

diff --git a/docs/user/algo_erwr.md b/docs/user/algo_erwr.md
@@ -1,4 +1,4 @@
-# ERWR
+# Episodic Reward Weighted Regression (ERWR)
 
 ```eval_rst
 +-------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

diff --git a/docs/user/algo_maml.md b/docs/user/algo_maml.md
@@ -1,4 +1,4 @@
-# MAML
+# Model-Agnostic Meta-Learning (MAML)
 
 ```eval_rst
 +-------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

diff --git a/docs/user/algo_mtppo.md b/docs/user/algo_mtppo.md
@@ -1,4 +1,4 @@
-# Multi-Task Proximal Policy Optimization (Multi-Task PPO)
+# Multi-Task Proximal Policy Optimization (MT-PPO)
 
 ```eval_rst
 +-------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

diff --git a/docs/user/algo_mtsac.md b/docs/user/algo_mtsac.md
@@ -1,4 +1,4 @@
-# Multi-Task Soft Actor-Critic
+# Multi-Task Soft Actor-Critic (MT-SAC)
 
 ```eval_rst
 .. list-table::
@@ -21,7 +21,7 @@
      - :ref:`mtsac_metaworld_ml1_pick_place`, :ref:`mtsac_metaworld_mt10`, :ref:`mtsac_metaworld_mt50`
 ```
 
-The Multi-Task Soft Actor-Critic (MTSAC) algorithm is the same as the [Soft Actor Critic (SAC)](algo_sac) algorithm, except for a small change called "disentangled alphas". Alpha is the entropy coefficient that is used to control exploration of the agent/policy. Disentangling alphas refers to having a separate alpha coefficients for every task learned by the policy. The alphas are accessed by using a one-hot encoding of an id that is assigned to each task.
+The Multi-Task Soft Actor-Critic (MT-SAC) algorithm is the same as the [Soft Actor Critic (SAC)](algo_sac) algorithm, except for a small change called "disentangled alphas". Alpha is the entropy coefficient that is used to control exploration of the agent/policy. Disentangling alphas refers to having a separate alpha coefficients for every task learned by the policy. The alphas are accessed by using a one-hot encoding of an id that is assigned to each task.
 
 
 ## Default Parameters

diff --git a/docs/user/algo_mttrpo.md b/docs/user/algo_mttrpo.md
@@ -1,4 +1,4 @@
-# Multi-Task TRPO
+# Multi-Task Trust Region Policy Optimization (MT-TRPO)
 
 ```eval_rst
 +-------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

diff --git a/docs/user/algo_ppo.md b/docs/user/algo_ppo.md
@@ -1,4 +1,4 @@
-# Proximal Policy Optimization
+# Proximal Policy Optimization (PPO)
 
 ```eval_rst
 +-------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

diff --git a/docs/user/algo_sac.md b/docs/user/algo_sac.md
@@ -1,4 +1,4 @@
-# Soft Actor-Critic
+# Soft Actor-Critic (SAC)
 
 ```eval_rst
 +-------------------+----------------------------------------------------------------------------------------------------------------+

diff --git a/docs/user/algo_trpo.md b/docs/user/algo_trpo.md
@@ -1,4 +1,4 @@
-# TRPO
+# Trust Region Policy Optimization (TRPO)
 
 ```eval_rst
 +-------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

diff --git a/docs/user/algo_vpg.md b/docs/user/algo_vpg.md
@@ -1,4 +1,4 @@
-# REINFORCE
+# REINFORCE (VPG)
 
 ```eval_rst
 +-------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

diff --git a/docs/user/cluster_setup.md b/docs/user/cluster_setup.md
@@ -1,4 +1,4 @@
-# Distribute experiments across machines
+# Distribute Experiments Across Machines
 
 This tutorial teaches you how to setup a [Prefect](https://docs.prefect.io/) +
 [Dask distributed](https://distributed.dask.org/en/latest/) cluster to

diff --git a/docs/user/custom_worker.md b/docs/user/custom_worker.md
@@ -1,4 +1,4 @@
-# Change how your algorithm samples (Implement a Custom Worker)
+# Change How Your Algorithm Samples (Implement a Custom Worker)
 
 ```eval_rst
 In sampling, :code:`Worker` perform rollouts to get samples. In this tutorial,

diff --git a/docs/user/ensure_your_experiments_are_reproducible.md b/docs/user/ensure_your_experiments_are_reproducible.md
@@ -1,5 +1,5 @@
 
-# Ensure your experiments are reproducible
+# Ensure Your Experiments are Reproducible
 
 Ensure the reproducibility of your experiments with comprehensive launcher
 files. Launcher files are used to initialize the algorithm, its components

diff --git a/docs/user/logging_plotting.md b/docs/user/logging_plotting.md
@@ -1,4 +1,4 @@
-# Logging and plotting
+# Logging and Plotting
 
 ## Logging
 

diff --git a/docs/user/max_resource_usage.md b/docs/user/max_resource_usage.md
@@ -1,4 +1,4 @@
-# Maximize resource usage
+# Maximize Resource Usage
 
 To accelerate running an experiment, we want to maximize the usage of resources
 (CPUs or GPUs).

diff --git a/docs/user/save_load_resume_exp.md b/docs/user/save_load_resume_exp.md
@@ -1,4 +1,4 @@
-# Save, load and resume experiments
+# Save, Load and Resume Experiments
 
 This document provides solutions to a variety of use cases
 regarding saving, loading and resuming of Garage experiments.

diff --git a/docs/user/setting_up_your_development_environment.md b/docs/user/setting_up_your_development_environment.md
@@ -1,4 +1,4 @@
-# Setting up your development environment
+# Setting Up Your Development Environment
 
 In this section you will learn how to install garage and its dependencies in a
 manner that allows for development. If you would like to contribute changes back

diff --git a/docs/user/use_pretrained_network_to_start_new_experiment.md b/docs/user/use_pretrained_network_to_start_new_experiment.md
@@ -1,4 +1,4 @@
-# Use a pre-trained network to start a new experiment
+# Use a Pre-Trained Network to Start a New Experiment
 
 In this section you will learn how to load a pre-trained network and use it in
 new experiments. In general, this process involves loading a snapshot, extracting