diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 90fa2ae..dc56e25 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -16,7 +16,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.6, 3.7, 3.8]
+        python-version: [3.6, 3.7, 3.8, 3.9]
 
     steps:
     - uses: actions/checkout@v2
diff --git a/CITATION.cff b/CITATION.cff
new file mode 100644
index 0000000..8696aa0
--- /dev/null
+++ b/CITATION.cff
@@ -0,0 +1,33 @@
+cff-version: 1.2.0
+message: "If you use this software, please cite it as below."
+authors:
+  -
+    family-names: Raffin
+    given-names: Antonin
+    orcid: "https://orcid.org/0000-0001-6036-6950"
+  -
+    family-names: Hill
+    given-names: Ashley
+  -
+    family-names: Enerstus
+    given-names: Maximilian
+  -
+    family-names: Gleave
+    given-names: Adam
+    orcid: "https://orcid.org/0000-0002-3467-528X"
+  -
+    family-names: Kanervisto
+    given-names: Anssi
+    orcid: "https://orcid.org/0000-0002-7479-4574"
+  -
+    family-names: Dormann
+    given-names: Noah
+
+title: "Stable Baselines3"
+abbreviation: SB3
+url: "https://github.com/DLR-RM/stable-baselines3"
+repository-code: "https://github.com/DLR-RM/stable-baselines3"
+version: 1.1.0
+date-released: 2020-05-05
+license: MIT
+# doi: # TODO when paper is released
diff --git a/docs/misc/changelog.rst b/docs/misc/changelog.rst
index 5022521..33991d0 100644
--- a/docs/misc/changelog.rst
+++ b/docs/misc/changelog.rst
@@ -3,6 +3,28 @@
 Changelog
 ==========
 
+
+Release 1.2.0a0 (WIP)
+-------------------------------
+
+Breaking Changes:
+^^^^^^^^^^^^^^^^^
+
+Bug Fixes:
+^^^^^^^^^^
+
+Deprecations:
+^^^^^^^^^^^^^
+
+Others:
+^^^^^^^
+- Fixed type annotation
+- Added python 3.9 to CI
+
+Documentation:
+^^^^^^^^^^^^^^
+
+
 Release 1.1.0 (2021-07-01)
 -------------------------------
 
diff --git a/sb3_contrib/tqc/tqc.py b/sb3_contrib/tqc/tqc.py
index 015f8d4..adead01 100644
--- a/sb3_contrib/tqc/tqc.py
+++ b/sb3_contrib/tqc/tqc.py
@@ -89,7 +89,7 @@ class TQC(OffPolicyAlgorithm):
         use_sde_at_warmup: bool = False,
         tensorboard_log: Optional[str] = None,
         create_eval_env: bool = False,
-        policy_kwargs: Dict[str, Any] = None,
+        policy_kwargs: Optional[Dict[str, Any]] = None,
         verbose: int = 0,
         seed: Optional[int] = None,
         device: Union[th.device, str] = "auto",
diff --git a/sb3_contrib/version.txt b/sb3_contrib/version.txt
index 9084fa2..0816bf0 100644
--- a/sb3_contrib/version.txt
+++ b/sb3_contrib/version.txt
@@ -1 +1 @@
-1.1.0
+1.2.0a0