Major refactor

utils/__init__.py

@@ -0,0 +1,5 @@
+from config import *
+try:
+    from tf_logger import Logger
+except:
+    from vanilla_logger import Logger

utils/config.py

@@ -0,0 +1,29 @@
+#######################################################################
+# Copyright (C) 2017 Shangtong Zhang(zhangshangtong.cpp@gmail.com)    #
+# Permission given to modify the code as long as you keep this        #
+# declaration at the top                                              #
+#######################################################################
+
+class Config:
+    def __init__(self):
+        self.task_fn = None
+        self.optimizer_fn = None
+        self.network_fn = None
+        self.policy_fn = None
+        self.replay_fn = None
+        self.discount = 0.99
+        self.target_network_update_freq = 0
+        self.max_episode_length = 0
+        self.exploration_steps = 0
+        self.logger = None
+        self.history_length = 1
+        self.test_interval = 100
+        self.test_repetitions = 50
+        self.double_q = False
+        self.tag = 'vanilla'
+        self.num_workers = 1
+        self.worker = None
+        self.update_interval = 1
+        self.gradient_clip = 40
+        self.entropy_weight = 0.01
+        self.gae_tau = 1.0

utils/tf_logger.py

@@ -0,0 +1,82 @@
+# Adapted from https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/04-utils/tensorboard/logger.py
+# Code referenced from https://gist.github.com/gyglim/1f8dfb1b5c82627ae3efcfbbadb9f514
+import tensorflow as tf
+import numpy as np
+import scipy.misc
+
+try:
+    from StringIO import StringIO  # Python 2.7
+except ImportError:
+    from io import BytesIO  # Python 3.x
+
+
+class Logger(object):
+    def __init__(self, log_dir, vanilla_logger, skip=False):
+        """Create a summary writer logging to log_dir."""
+        self.writer = tf.summary.FileWriter(log_dir)
+        self.info = vanilla_logger.info
+        self.debug = vanilla_logger.debug
+        self.warning = vanilla_logger.warning
+        self.skip = skip
+
+    def scalar_summary(self, tag, value, step):
+        if self.skip:
+            return
+        """Log a scalar variable."""
+        summary = tf.Summary(value=[tf.Summary.Value(tag=tag, simple_value=value)])
+        self.writer.add_summary(summary, step)
+
+    def image_summary(self, tag, images, step):
+        if self.skip:
+            return
+        """Log a list of images."""
+
+        img_summaries = []
+        for i, img in enumerate(images):
+            # Write the image to a string
+            try:
+                s = StringIO()
+            except:
+                s = BytesIO()
+            scipy.misc.toimage(img).save(s, format="png")
+
+            # Create an Image object
+            img_sum = tf.Summary.Image(encoded_image_string=s.getvalue(),
+                                       height=img.shape[0],
+                                       width=img.shape[1])
+            # Create a Summary value
+            img_summaries.append(tf.Summary.Value(tag='%s/%d' % (tag, i), image=img_sum))
+
+        # Create and write Summary
+        summary = tf.Summary(value=img_summaries)
+        self.writer.add_summary(summary, step)
+
+    def histo_summary(self, tag, values, step, bins=1000):
+        if self.skip:
+            return
+        """Log a histogram of the tensor of values."""
+
+        # Create a histogram using numpy
+        counts, bin_edges = np.histogram(values, bins=bins)
+
+        # Fill the fields of the histogram proto
+        hist = tf.HistogramProto()
+        hist.min = float(np.min(values))
+        hist.max = float(np.max(values))
+        hist.num = int(np.prod(values.shape))
+        hist.sum = float(np.sum(values))
+        hist.sum_squares = float(np.sum(values ** 2))
+
+        # Drop the start of the first bin
+        bin_edges = bin_edges[1:]
+
+        # Add bin edges and counts
+        for edge in bin_edges:
+            hist.bucket_limit.append(edge)
+        for c in counts:
+            hist.bucket.append(c)
+
+        # Create and write Summary
+        summary = tf.Summary(value=[tf.Summary.Value(tag=tag, histo=hist)])
+        self.writer.add_summary(summary, step)
+        self.writer.flush()

utils/vanilla_logger.py

@@ -0,0 +1,21 @@
+import numpy as np
+
+class Logger(object):
+    def __init__(self, log_dir, vanilla_logger, skip=False):
+        """Create a summary writer logging to log_dir."""
+        self.info = vanilla_logger.info
+        self.debug = vanilla_logger.debug
+        self.warning = vanilla_logger.warning
+        self.skip = skip
+
+    def scalar_summary(self, tag, value, step):
+        if self.skip:
+            return
+
+    def image_summary(self, tag, images, step):
+        if self.skip:
+            return
+
+    def histo_summary(self, tag, values, step, bins=1000):
+        if self.skip:
+            return