docs: update api documents (#191)

* feat(statistics tools): support statistics tools for experiments launched by omnisafe (#157) * docs: update API documentation * chore: clean the code * fix: fix duplicate files * fix: delete duplicate conf.py * docs: update tools docs * chore: clean the docs * docs: update app docs * fix: fix conf.py * fix: fix cli docs * docs: update omnisafe usage * fix: [pre-commit.ci] auto fixes [...] * refactor: refactor docs structure * docs(foundations): rename docs file * docs: update introduction * fix: [pre-commit.ci] auto fixes [...] * fix: fix spelling * fix: [pre-commit.ci] auto fixes [...] * fix: fix code block * docs: update comment * docs: fix ggrammer * docs(models, envs): update api docs * docs: update title * docs: update model docs * docs(adapters): update API docs * style: clean the docs * fix: revert ruff * docs: fix spelling * docs: update start example * docs: fix typo * docs: update notation table * docs: fix notation table * docs(CUP): update cup docs * docs(TRPO): update trpo docs * fix: fix exp grid * fix: fix exp grid * chore: update version --------- Co-authored-by: muchvo <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
PKU-Alignment · Apr 1, 2023 · 3df1725 · 3df1725
1 parent 324d257
commit 3df1725
Show file tree

Hide file tree

Showing 58 changed files with 2,039 additions and 1,102 deletions.
diff --git a/docs/source/baserl/ppo.rst b/docs/source/baserl/ppo.rst
diff --git a/docs/source/baserl/trpo.rst b/docs/source/baserl/trpo.rst
diff --git a/docs/source/baserlapi/on_policy.rst b/docs/source/baserlapi/on_policy.rst
@@ -25,7 +25,7 @@ Policy Gradient
         :members:
         :private-members:
 
-        .. automethod:: __init__
+
 
 Natural Policy Gradient
 -----------------------
@@ -41,7 +41,11 @@ Natural Policy Gradient
         :members:
         :private-members:
 
-        .. automethod:: __init__
+
+
+
+.. _trpoapi:
+
 
 Trust Region Policy Optimization
 --------------------------------
@@ -57,7 +61,11 @@ Trust Region Policy Optimization
         :members:
         :private-members:
 
-        .. automethod:: __init__
+
+
+
+.. _ppoapi:
+
 
 Proximal Policy Optimization
 ----------------------------
@@ -72,5 +80,3 @@ Proximal Policy Optimization
     .. autoclass:: PPO
         :members:
         :private-members:
-
-        .. automethod:: __init__
diff --git a/docs/source/common/buffer.rst b/docs/source/common/buffer.rst
@@ -26,7 +26,7 @@ Base Buffer
         :members:
         :private-members:
 
-        .. automethod:: __init__
+
 
 On Policy Buffer
 ----------------
@@ -42,7 +42,7 @@ On Policy Buffer
         :members:
         :private-members:
 
-        .. automethod:: __init__
+
 
 Off Policy buffer
 -----------------
@@ -58,7 +58,7 @@ Off Policy buffer
         :members:
         :private-members:
 
-        .. automethod:: __init__
+
 
 Vector On Policy Buffer
 -----------------------
@@ -74,7 +74,7 @@ Vector On Policy Buffer
         :members:
         :private-members:
 
-        .. automethod:: __init__
+
 
 Vector Off Policy Buffer
 ------------------------
@@ -89,5 +89,3 @@ Vector Off Policy Buffer
     .. autoclass:: VectorOffPolicyBuffer
         :members:
         :private-members:
-
-        .. automethod:: __init__
diff --git a/docs/source/common/exp_grid.rst b/docs/source/common/exp_grid.rst
@@ -20,5 +20,3 @@ Experiment Grid
     .. autoclass:: ExperimentGrid
         :members:
         :private-members:
-
-        .. automethod:: __init__
diff --git a/docs/source/common/lagrange.rst b/docs/source/common/lagrange.rst
@@ -21,8 +21,6 @@ Lagrange Multiplier
         :members:
         :private-members:
 
-        .. automethod:: __init__
-
 
 .. currentmodule:: omnisafe.common.pid_lagrange
 
@@ -43,5 +41,3 @@ PIDLagrange
     .. autoclass:: PIDLagrangian
         :members:
         :private-members:
-
-        .. automethod:: __init__
diff --git a/docs/source/common/logger.rst b/docs/source/common/logger.rst
@@ -20,5 +20,3 @@ Logger
     .. autoclass:: Logger
         :members:
         :private-members:
-
-        .. automethod:: __init__
diff --git a/docs/source/common/normalizer.rst b/docs/source/common/normalizer.rst
@@ -18,5 +18,3 @@ Normalizer
     .. autoclass:: Normalizer
         :members:
         :private-members:
-
-        .. automethod:: __init__
diff --git a/docs/source/envs/adapter.rst b/docs/source/envs/adapter.rst
@@ -0,0 +1,47 @@
+Adapter
+=======
+
+.. currentmodule:: omnisafe.adapter
+
+
+Online Adapter
+--------------
+
+.. card::
+    :class-header: sd-bg-success sd-text-white
+    :class-card: sd-outline-success  sd-rounded-1
+
+    Documentation
+    ^^^
+
+    .. autoclass:: OnlineAdapter
+        :members:
+        :private-members:
+
+On Policy Adapter
+-----------------
+
+.. card::
+    :class-header: sd-bg-success sd-text-white
+    :class-card: sd-outline-success  sd-rounded-1
+
+    Documentation
+    ^^^
+
+    .. autoclass:: OnPolicyAdapter
+        :members:
+        :private-members:
+
+Off Policy Adapter
+------------------
+
+.. card::
+    :class-header: sd-bg-success sd-text-white
+    :class-card: sd-outline-success  sd-rounded-1
+
+    Documentation
+    ^^^
+
+    .. autoclass:: OffPolicyAdapter
+        :members:
+        :private-members:
diff --git a/docs/source/envs/core.rst b/docs/source/envs/core.rst
@@ -0,0 +1,56 @@
+Core
+====
+
+.. currentmodule:: omnisafe.envs.core
+
+.. autosummary::
+
+    CMDP
+    Wrapper
+    EnvRegister
+
+CMDP
+----
+
+.. card::
+    :class-header: sd-bg-success sd-text-white
+    :class-card: sd-outline-success  sd-rounded-1
+
+    Documentation
+    ^^^
+
+    .. autoclass:: CMDP
+        :members:
+        :private-members:
+
+Wrapper
+-------
+
+.. card::
+    :class-header: sd-bg-success sd-text-white
+    :class-card: sd-outline-success  sd-rounded-1
+
+    Documentation
+    ^^^
+
+    .. autoclass:: Wrapper
+        :members:
+        :private-members:
+
+Make an environment
+-------------------
+
+.. card::
+    :class-header: sd-bg-success sd-text-white
+    :class-card: sd-outline-success  sd-rounded-1
+
+    Documentation
+    ^^^
+
+    .. autoclass:: EnvRegister
+        :members:
+        :private-members:
+
+
+
+    .. autofunction:: make
diff --git a/docs/source/envs/safety_gymnasium.rst b/docs/source/envs/safety_gymnasium.rst
@@ -0,0 +1,18 @@
+Safety Gymnasium Environment
+============================
+
+.. currentmodule:: omnisafe.envs.safety_gymnasium_env
+
+Safety Gymnasium Interface
+--------------------------
+
+.. card::
+    :class-header: sd-bg-success sd-text-white
+    :class-card: sd-outline-success  sd-rounded-1
+
+    Documentation
+    ^^^
+
+    .. autoclass:: SafetyGymnasiumEnv
+        :members:
+        :private-members:
diff --git a/docs/source/envs/wrapper.rst b/docs/source/envs/wrapper.rst
@@ -0,0 +1,114 @@
+Wrapper
+=======
+
+.. currentmodule:: omnisafe.envs.wrapper
+
+.. autosummary::
+
+    TimeLimit
+    AutoReset
+    ObsNormalize
+    RewardNormalize
+    CostNormalize
+    ActionScale
+    Unsqueeze
+
+Time Limit Wrapper
+------------------
+
+.. card::
+    :class-header: sd-bg-success sd-text-white
+    :class-card: sd-outline-success  sd-rounded-1
+
+    Documentation
+    ^^^
+
+    .. autoclass:: TimeLimit
+        :members:
+        :private-members:
+
+Auto Reset Wrapper
+------------------
+
+.. card::
+    :class-header: sd-bg-success sd-text-white
+    :class-card: sd-outline-success  sd-rounded-1
+
+    Documentation
+    ^^^
+
+    .. autoclass:: AutoReset
+        :members:
+        :private-members:
+
+
+Observation Normalization Wrapper
+---------------------------------
+
+.. card::
+    :class-header: sd-bg-success sd-text-white
+    :class-card: sd-outline-success  sd-rounded-1
+
+    Documentation
+    ^^^
+
+    .. autoclass:: ObsNormalize
+        :members:
+        :private-members:
+
+Reward Normalization Wrapper
+----------------------------
+
+.. card::
+    :class-header: sd-bg-success sd-text-white
+    :class-card: sd-outline-success  sd-rounded-1
+
+    Documentation
+    ^^^
+
+    .. autoclass:: RewardNormalize
+        :members:
+        :private-members:
+
+Cost Normalization Wrapper
+--------------------------
+
+.. card::
+    :class-header: sd-bg-success sd-text-white
+    :class-card: sd-outline-success  sd-rounded-1
+
+    Documentation
+    ^^^
+
+    .. autoclass:: CostNormalize
+        :members:
+        :private-members:
+
+Action Scale
+------------
+
+.. card::
+    :class-header: sd-bg-success sd-text-white
+    :class-card: sd-outline-success  sd-rounded-1
+
+    Documentation
+    ^^^
+
+    .. autoclass:: ActionScale
+        :members:
+        :private-members:
+
+
+Unsqueeze Wrapper
+-----------------
+
+.. card::
+    :class-header: sd-bg-success sd-text-white
+    :class-card: sd-outline-success  sd-rounded-1
+
+    Documentation
+    ^^^
+
+    .. autoclass:: Unsqueeze
+        :members:
+        :private-members: