Merge pull request #1065 from tensorlayer/reinforcement-learning

Reinforcement learning examples update

Author: quantumiracle

docker/pypi_list.py

@@ -32,11 +32,7 @@
     logger.debug("prerelease: %s" % args.prerelease)
     logger.debug("debug: %s" % args.debug)
 
-    finder = pip._internal.index.PackageFinder(
-        [],
-        ['https://pypi.python.org/simple'],
-        session=requests.Session()
-    )
+    finder = pip._internal.index.PackageFinder([], ['https://pypi.python.org/simple'], session=requests.Session())
     results = finder.find_all_candidates(args.package)
     tmp_versions = [str(p.version) for p in results]
 

docker/version_prefix.py

@@ -6,10 +6,7 @@
     parser = argparse.ArgumentParser(description='Determine the version prefix to apply depending on the version name')
 
     parser.add_argument(
-        '--version',
-        type=str,
-        required=True,
-        help='The Package Version to be installed in the container'
+        '--version', type=str, required=True, help='The Package Version to be installed in the container'
     )
 
     parser.add_argument('--debug', help='Print debug information', action='store_true')

docs/conf.py

@@ -19,7 +19,7 @@
 #
 import os, sys, datetime
 sys.path.insert(0, os.path.abspath("../"))  # Important
-sys.path.insert(0, os.path.abspath(os.path.join("..", "tensorlayer"))) # Important
+sys.path.insert(0, os.path.abspath(os.path.join("..", "tensorlayer")))  # Important
 
 from package_info import __shortversion__
 from package_info import __version__
@@ -159,7 +159,6 @@
 # If true, `todo` and `todoList` produce output, else they produce nothing.
 todo_include_todos = False
 
-
 # -- Options for HTML output ----------------------------------------------
 
 # The theme to use for HTML and HTML Help pages.  See the documentation for
@@ -284,29 +283,28 @@
 # -- Options for LaTeX output ---------------------------------------------
 
 latex_elements = {
-     # The paper size ('letterpaper' or 'a4paper').
-     #
-     # 'papersize': 'letterpaper',
+    # The paper size ('letterpaper' or 'a4paper').
+    #
+    # 'papersize': 'letterpaper',
 
-     # The font size ('10pt', '11pt' or '12pt').
-     #
-     # 'pointsize': '10pt',
+    # The font size ('10pt', '11pt' or '12pt').
+    #
+    # 'pointsize': '10pt',
 
-     # Additional stuff for the LaTeX preamble.
-     #
-     # 'preamble': '',
+    # Additional stuff for the LaTeX preamble.
+    #
+    # 'preamble': '',
 
-     # Latex figure (float) alignment
-     #
-     # 'figure_align': 'htbp',
+    # Latex figure (float) alignment
+    #
+    # 'figure_align': 'htbp',
 }
 
 # Grouping the document tree into LaTeX files. List of tuples
 # (source start file, target name, title,
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
-    (master_doc, 'TensorLayer.tex', 'TensorLayer Documentation',
-     'TensorLayer contributors', 'manual'),
+    (master_doc, 'TensorLayer.tex', 'TensorLayer Documentation', 'TensorLayer contributors', 'manual'),
 ]
 
 # The name of an image file (relative to this directory) to place at the top of
@@ -335,30 +333,26 @@
 #
 # latex_domain_indices = True
 
-
 # -- Options for manual page output ---------------------------------------
 
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
-man_pages = [
-    (master_doc, 'tensorlayer', 'TensorLayer Documentation',
-     [author], 1)
-]
+man_pages = [(master_doc, 'tensorlayer', 'TensorLayer Documentation', [author], 1)]
 
 # If true, show URL addresses after external links.
 #
 # man_show_urls = False
 
-
 # -- Options for Texinfo output -------------------------------------------
 
 # Grouping the document tree into Texinfo files. List of tuples
 # (source start file, target name, title, author,
 #  dir menu entry, description, category)
 texinfo_documents = [
-    (master_doc, 'TensorLayer', 'TensorLayer Documentation',
-     author, 'TensorLayer', 'Deep learning and Reinforcement learning library for Researchers and Engineers.',
-     'Miscellaneous'),
+    (
+        master_doc, 'TensorLayer', 'TensorLayer Documentation', author, 'TensorLayer',
+        'Deep learning and Reinforcement learning library for Researchers and Engineers.', 'Miscellaneous'
+    ),
 ]
 
 # Documents to append as an appendix to all manuals.
@@ -377,7 +371,6 @@
 #
 # texinfo_no_detailmenu = False
 
-
 # -- Options for Epub output ----------------------------------------------
 
 # Bibliographic Dublin Core info.

examples/data_process/tutorial_fast_affine_transform.py

@@ -8,10 +8,10 @@
 import multiprocessing
 import time
 
+import cv2
 import numpy as np
 import tensorflow as tf
 
-import cv2
 import tensorlayer as tl
 
 # tl.logging.set_verbosity(tl.logging.DEBUG)

examples/data_process/tutorial_tfrecord3.py

@@ -231,8 +231,8 @@ def distort_image(image, thread_id):
 
 
 def prefetch_input_data(
-    reader, file_pattern, is_training, batch_size, values_per_shard, input_queue_capacity_factor=16,
-    num_reader_threads=1, shard_queue_name="filename_queue", value_queue_name="input_queue"
+        reader, file_pattern, is_training, batch_size, values_per_shard, input_queue_capacity_factor=16,
+        num_reader_threads=1, shard_queue_name="filename_queue", value_queue_name="input_queue"
 ):
     """Prefetches string values from disk into an input queue.
 

examples/reinforcement_learning/.gitignore

@@ -0,0 +1,2 @@
+model/
+image/

examples/reinforcement_learning/README.md

@@ -20,7 +20,7 @@
 <br/>
 -->
 
-This repository contains the implementation of most popular reinforcement learning algorithms with Tensorlayer 2.0, supporting [Tensorflow 2.0](https://www.tensorflow.org/alpha/guide/effective_tf2). We aim to make the reinforcement learning tutorial for each algorithm simple and straight-forward to use, as this would not only benefit new learners of reinforcement learning but also provide convenience for senior researchers to testify their new ideas quickly. In addition to this project, we also released a [RL zoo](https://github.com/tensorlayer/RLzoo) for industrial users.
+This repository contains implementation of most popular reinforcement learning algorithms with Tensorlayer 2.0, supporting [Tensorflow 2.0](https://www.tensorflow.org/alpha/guide/effective_tf2). We aim to make the reinforcement learning tutorial for each algorithm simple and straight-forward to use, as this would not only benefits new learners of reinforcement learning, but also provide convenience for senior researchers to testify their new ideas quickly.
 
 ## Prerequisites:
 
@@ -46,6 +46,8 @@ For each tutorial, open a terminal and run:
 
 The tutorial algorithms follow the same basic structure, as shown in file: [`./tutorial_format.py`](https://github.com/tensorlayer/tensorlayer/blob/reinforcement-learning/examples/reinforcement_learning/tutorial_format.py)
 
+The pretrained models and learning curves for each algorithm are stored [here](https://github.com/tensorlayer/pretrained-models). You can download the models and load the weights in the policies for tests.
+
 ## Table of Contents:
 ### value-based
 | Algorithms      | Action Space | Tutorial Env   | Papers |
@@ -123,18 +125,19 @@ The tutorial algorithms follow the same basic structure, as shown in file: [`./t
 
   ```
   We implement Double DQN, Dueling DQN and Noisy DQN here.
-
+  
   -The max operator in standard DQN uses the same values both to select and to evaluate an action by:
-
+  
      Q(s_t, a_t) = R\_{t+1\} + gamma \* max\_{a}Q\_\{target\}(s_{t+1}, a).
-
+  
   -Double DQN proposes to use following evaluation to address overestimation problem of max operator:
-
+  
      Q(s_t, a_t) = R\_{t+1\} + gamma \* Q\_{target}(s\_\{t+1\}, max{a}Q(s_{t+1}, a)).
-
+  
   -Dueling DQN uses dueling architecture where the value of state and the advantage of each action is estimated separately.
-
+  
   -Noisy DQN propose to explore by adding parameter noises.
+  ```
 
 
   ```
@@ -339,3 +342,5 @@ Our env wrapper: `./tutorial_wrappers.py`
 - @Tokarev-TT-33 Tianyang Yu @initial-h Hongming Zhang : PG, DDPG, PPO, DPPO, TRPO
 - @Officium Yanhua Huang: C51, DQN_variants, prioritized_replay, wrappers.
 
+
+  ```