Big refactor (#124)

* massive revision inspired by soup: algo folder works

* porting rl commands, WIP

* various

* git subrepo push --remote=git@github.com:openai/codegen.git --branch=refactor codegen

subrepo:
  subdir:   "codegen"
  merged:   "aa27e069"
upstream:
  origin:   "git@github.com:openai/codegen.git"
  branch:   "refactor"
  commit:   "aa27e069"
git-subrepo:
  version:  "0.4.0"
  origin:   "git@github.com:ingydotnet/git-subrepo.git"
  commit:   "74339e8"

* various

* rewrite RL stuff in new framework

* fix almost everything

* woohoo tests pass

* more tests

* reformatting

* fixes

* write tests for embeddings

* re-remove cg2

* pylint

* minor

* move smooth_helpers import; seems to cause nondeterministic failure in parallel pytest

baselines/common/distributions.py

@@ -53,6 +53,9 @@ class PdType(object):
     def sample_placeholder(self, prepend_shape, name=None):
         return tf.placeholder(dtype=self.sample_dtype(), shape=prepend_shape+self.sample_shape(), name=name)
 
+    def __eq__(self, other):
+        return (type(self) == type(other)) and (self.__dict__ == other.__dict__)
+
 class CategoricalPdType(PdType):
     def __init__(self, ncat):
         self.ncat = ncat