[rllib] Evaluators and Optimizers Refactoring (#1339)

python/ray/rllib/optimizers/sample_batch.py

@@ -23,6 +23,7 @@ class SampleBatch(object):
             assert type(k) == str, self
             lengths.append(len(v))
         assert len(set(lengths)) == 1, "data columns must be same length"
+        self.count = lengths[0]
 
     @staticmethod
     def concat_samples(samples):
@@ -56,8 +57,7 @@ class SampleBatch(object):
             {"a": 3, "b": 6}
         """
 
-        num_rows = len(list(self.data.values())[0])
-        for i in range(num_rows):
+        for i in range(self.count):
             row = {}
             for k in self.data.keys():
                 row[k] = self[k][i]
@@ -77,11 +77,16 @@ class SampleBatch(object):
             out.append(self.data[k])
         return out
 
+    def shuffle(self):
+        permutation = np.random.permutation(self.count)
+        for key, val in self.data.items():
+            self.data[key] = val[permutation]
+
     def __getitem__(self, key):
         return self.data[key]
 
     def __str__(self):
-        return str(self.data)
+        return "SampleBatch({})".format(str(self.data))
 
     def __repr__(self):
-        return str(self.data)
+        return "SampleBatch({})".format(str(self.data))

python/ray/rllib/optimizers/util.py

@@ -1,33 +0,0 @@
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-
-import time
-
-# TODO(ekl) move this to a common location
-from ray.rllib.ppo.filter import RunningStat
-
-
-class TimerStat(RunningStat):
-    """A running stat for conveniently logging the duration of a code block.
-
-    Example:
-        wait_timer = TimeStat()
-        with wait_timer:
-            ray.wait(...)
-
-    Note that this class is *not* thread-safe.
-    """
-
-    def __init__(self):
-        RunningStat.__init__(self, ())
-        self._start_time = None
-
-    def __enter__(self):
-        assert self._start_time is None, "concurrent updates not supported"
-        self._start_time = time.monotonic()
-
-    def __exit__(self, type, value, tb):
-        assert self._start_time is not None
-        self.push(time.monotonic() - self._start_time)
-        self._start_time = None