RL unplugged implementation with tests (#452)

* RL unplugged implementation with tests

* Fix NEWS.md

* Fix cspell

* Update README.md

* Setup docs

* Update README.md

* tweak docs

* Make changes in dependencies

* Update dependencies

* add .gitignore

* Remove cached docs

Co-authored-by: Jun Tian <[email protected]>

Author: Mobius1D

.cspell/cspell.json

@@ -121,6 +121,22 @@
         "gzopen",
         "turbulences",
         "Decompressor",
+        "MADDPG",
+        "Caglar",
+        "Gulcehre",
+        "Novikov",
+        "Gómez",
+        "Colmenarejo",
+        "Zolna",
+        "Merel",
+        "Mankowitz",
+        "Paduraru",
+        "Dulac",
+        "Nachum",
+        "Heess",
+        "Nando",
+        "Freitas",
+        "bufsize",
         "PLAS",
         "CRR",
         "reparamaterize",

NEWS.md

@@ -22,6 +22,7 @@
 - Add functionality for fetching d4rl datasets as an iterable DataSet. Credits: https://arxiv.org/abs/2004.07219
 - This supports d4rl and d4rl-pybullet and Google Research DQN atari datasets.
 - Uses DataDeps for data dependency management.
+- This package also supports RL Unplugged Atari Datasets.
 
 ## [email protected]
 

src/ReinforcementLearningDatasets/.gitignore

@@ -0,0 +1 @@
+/docs/build