SAC algorithm (#282)

* SAC algorithm

* SAC - updates to agent (learn_from_batch), sac_head and sac_q_head to fix problem in gradient calculation. Now SAC agents is able to train.
gym_environment - fixing an error in access to gym.spaces

* Soft Actor Critic - code cleanup

* code cleanup

* V-head initialization fix

* SAC benchmarks

* SAC Documentation

* typo fix

* documentation fixes

* documentation and version update

* README typo

docs/_static/css/custom.css

@@ -1,61 +0,0 @@
-/* Docs background */
-.wy-side-nav-search{
-  background-color: #043c74;
-}
-
-/* Mobile version */
-.wy-nav-top{
-  background-color: #043c74;
-}
-
-
-.green {
-    color: green;
-}
-
-.red {
-    color: red;
-}
-
-.blue {
-    color: blue;
-}
-
-.yellow {
-    color: yellow;
-}
-
-.badge {
-    border: 2px;
-    border-style: solid;
-    border-color: #6C8EBF;
-    border-radius: 5px;
-    padding: 3px 15px 3px 15px;
-    margin: 5px;
-    display: inline-block;
-    font-weight: bold;
-    font-size: 16px;
-    background: #DAE8FC;
-}
-
-.badge:hover {
-    cursor: pointer;
-}
-
-.badge > a {
-    color: black;
-}
-
-.bordered-container {
-    border: 0px;
-    border-style: solid;
-    border-radius: 8px;
-    padding: 15px;
-    margin-bottom: 20px;
-    background: #f2f2f2;
-}
-
-.questionnaire {
-    font-size: 1.2em;
-    line-height: 1.5em;
-}