polish(nyz): polish api doc details

PaParaZz1 · PaParaZz1 · commit d88ebe2bc275 · 2024-07-06T17:49:14.000+08:00
diff --git a/ding/bonus/a2c.py b/ding/bonus/a2c.py
@@ -70,7 +70,7 @@ def __init__(
             - model (:obj:`torch.nn.Module`): The model of A2C algorithm, which should be an instance of class \
                 :class:`ding.model.VAC`. \
                 If not specified, a default model will be generated according to the configuration.
-            - cfg (:obj:Union[EasyDict, dict]): The configuration of A2C algorithm, which is a dict. \
+            - cfg (:obj:`Union[EasyDict, dict]`): The configuration of A2C algorithm, which is a dict. \
                 Default to None. If not specified, the default configuration will be used. \
                 The default configuration can be found in ``ding/config/example/A2C/gym_lunarlander_v2.py``.
             - policy_state_dict (:obj:`str`): The path of policy state dict saved by PyTorch a in local file. \
diff --git a/ding/bonus/c51.py b/ding/bonus/c51.py
@@ -68,9 +68,8 @@ def __init__(
             - exp_name (:obj:`str`): The name of this experiment, which will be used to create the folder to save \
                 log data. Default to None. If not specified, the folder name will be ``env_id``-``algorithm``.
             - model (:obj:`torch.nn.Module`): The model of C51 algorithm, which should be an instance of class \
-                :class:`ding.model.C51DQN`. \
-                If not specified, a default model will be generated according to the configuration.
-            - cfg (:obj:Union[EasyDict, dict]): The configuration of C51 algorithm, which is a dict. \
+                :class:`ding.model.C51DQN`. If not specified, a default model will be generated according to the config.
+            - cfg (:obj:`Union[EasyDict, dict]`): The configuration of C51 algorithm, which is a dict. \
                 Default to None. If not specified, the default configuration will be used. \
                 The default configuration can be found in ``ding/config/example/C51/gym_lunarlander_v2.py``.
             - policy_state_dict (:obj:`str`): The path of policy state dict saved by PyTorch a in local file. \
diff --git a/ding/bonus/ddpg.py b/ding/bonus/ddpg.py
@@ -70,7 +70,7 @@ def __init__(
             - model (:obj:`torch.nn.Module`): The model of DDPG algorithm, which should be an instance of class \
                 :class:`ding.model.ContinuousQAC`. \
                 If not specified, a default model will be generated according to the configuration.
-            - cfg (:obj:Union[EasyDict, dict]): The configuration of DDPG algorithm, which is a dict. \
+            - cfg (:obj:`Union[EasyDict, dict]`): The configuration of DDPG algorithm, which is a dict. \
                 Default to None. If not specified, the default configuration will be used. \
                 The default configuration can be found in ``ding/config/example/DDPG/gym_lunarlander_v2.py``.
             - policy_state_dict (:obj:`str`): The path of policy state dict saved by PyTorch a in local file. \
diff --git a/ding/bonus/dqn.py b/ding/bonus/dqn.py
@@ -70,7 +70,7 @@ def __init__(
             - model (:obj:`torch.nn.Module`): The model of DQN algorithm, which should be an instance of class \
                 :class:`ding.model.DQN`. \
                 If not specified, a default model will be generated according to the configuration.
-            - cfg (:obj:Union[EasyDict, dict]): The configuration of DQN algorithm, which is a dict. \
+            - cfg (:obj:`Union[EasyDict, dict]`): The configuration of DQN algorithm, which is a dict. \
                 Default to None. If not specified, the default configuration will be used. \
                 The default configuration can be found in ``ding/config/example/DQN/gym_lunarlander_v2.py``.
             - policy_state_dict (:obj:`str`): The path of policy state dict saved by PyTorch a in local file. \
diff --git a/ding/bonus/pg.py b/ding/bonus/pg.py
@@ -68,7 +68,7 @@ def __init__(
             - model (:obj:`torch.nn.Module`): The model of PG algorithm, which should be an instance of class \
                 :class:`ding.model.PG`. \
                 If not specified, a default model will be generated according to the configuration.
-            - cfg (:obj:Union[EasyDict, dict]): The configuration of PG algorithm, which is a dict. \
+            - cfg (:obj:`Union[EasyDict, dict]`): The configuration of PG algorithm, which is a dict. \
                 Default to None. If not specified, the default configuration will be used. \
                 The default configuration can be found in ``ding/config/example/PG/gym_lunarlander_v2.py``.
             - policy_state_dict (:obj:`str`): The path of policy state dict saved by PyTorch a in local file. \
diff --git a/ding/bonus/ppo_offpolicy.py b/ding/bonus/ppo_offpolicy.py
@@ -70,7 +70,7 @@ def __init__(
             - model (:obj:`torch.nn.Module`): The model of PPO (offpolicy) algorithm, \
                 which should be an instance of class :class:`ding.model.VAC`. \
                 If not specified, a default model will be generated according to the configuration.
-            - cfg (:obj:Union[EasyDict, dict]): The configuration of PPO (offpolicy) algorithm, which is a dict. \
+            - cfg (:obj:`Union[EasyDict, dict]`): The configuration of PPO (offpolicy) algorithm, which is a dict. \
                 Default to None. If not specified, the default configuration will be used. \
                 The default configuration can be found in ``ding/config/example/PPO (offpolicy)/gym_lunarlander_v2.py``.
             - policy_state_dict (:obj:`str`): The path of policy state dict saved by PyTorch a in local file. \
diff --git a/ding/bonus/sac.py b/ding/bonus/sac.py
@@ -71,7 +71,7 @@ def __init__(
             - model (:obj:`torch.nn.Module`): The model of SAC algorithm, which should be an instance of class \
                 :class:`ding.model.ContinuousQAC`. \
                 If not specified, a default model will be generated according to the configuration.
-            - cfg (:obj:Union[EasyDict, dict]): The configuration of SAC algorithm, which is a dict. \
+            - cfg (:obj:`Union[EasyDict, dict]`): The configuration of SAC algorithm, which is a dict. \
                 Default to None. If not specified, the default configuration will be used. \
                 The default configuration can be found in ``ding/config/example/SAC/gym_lunarlander_v2.py``.
             - policy_state_dict (:obj:`str`): The path of policy state dict saved by PyTorch a in local file. \
diff --git a/ding/envs/env_manager/base_env_manager.py b/ding/envs/env_manager/base_env_manager.py
@@ -124,7 +124,7 @@ def __init__(
 
         .. note::
             For more details about how to merge config, please refer to the system document of DI-engine \
-            (`en link <../03_system/config.html>`_).
+            (`en link1 <../03_system/config.html>`_).
         """
         self._cfg = cfg
         self._env_fn = env_fn
@@ -484,7 +484,7 @@ def seed(self, seed: Union[Dict[int, int], List[int], int], dynamic_seed: bool =
 
         .. note::
             For more details about ``dynamic_seed``, please refer to the best practice document of DI-engine \
-            (`en link <../04_best_practice/random_seed.html>`_).
+            (`en link2 <../04_best_practice/random_seed.html>`_).
         """
         if isinstance(seed, numbers.Integral):
             seed = [seed + i for i in range(self.env_num)]
@@ -580,7 +580,7 @@ class BaseEnvManagerV2(BaseEnvManager):
 
     .. note::
         For more details about new task pipeline, please refer to the system document of DI-engine \
-        (`system en link <../03_system/index.html>`_).
+        (`system en link3 <../03_system/index.html>`_).
 
     Interfaces:
         reset, step, seed, close, enable_save_replay, launch, default_config, reward_shaping, enable_save_figure
diff --git a/ding/model/template/qgpo.py b/ding/model/template/qgpo.py
@@ -418,9 +418,9 @@ def q_loss_fn(self, a, s, r, s_, d, fake_a_, discount=0.99):
             - a (:obj:`torch.Tensor`): The input action.
             - s (:obj:`torch.Tensor`): The input state.
             - r (:obj:`torch.Tensor`): The input reward.
-            - s_ (:obj:`torch.Tensor`): The input next state.
+            - s\_ (:obj:`torch.Tensor`): The input next state.
             - d (:obj:`torch.Tensor`): The input done.
-            - fake_a_ (:obj:`torch.Tensor`): The input fake action.
+            - fake_a (:obj:`torch.Tensor`): The input fake action.
             - discount (:obj:`float`): The discount factor.
         """
 
diff --git a/ding/policy/qgpo.py b/ding/policy/qgpo.py
@@ -13,12 +13,11 @@
 @POLICY_REGISTRY.register('qgpo')
 class QGPOPolicy(Policy):
     """
-       Overview:
-            Policy class of QGPO algorithm
-            Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning
-            https://arxiv.org/abs/2304.12824
-        Interfaces:
-            ``__init__``, ``forward``, ``learn``, ``eval``, ``state_dict``, ``load_state_dict``
+    Overview:
+        Policy class of QGPO algorithm (https://arxiv.org/abs/2304.12824).
+        Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning
+    Interfaces:
+        ``__init__``, ``forward``, ``learn``, ``eval``, ``state_dict``, ``load_state_dict``
     """
 
     config = dict(
diff --git a/ding/rl_utils/value_rescale.py b/ding/rl_utils/value_rescale.py
@@ -5,11 +5,11 @@ def value_transform(x: torch.Tensor, eps: float = 1e-2) -> torch.Tensor:
     """
     Overview:
         A function to reduce the scale of the action-value function.
-        :math: `h(x) = sign(x)(\sqrt{(abs(x)+1)} - 1) + \eps * x` .
+        :math: `h(x) = sign(x)(\sqrt{(abs(x)+1)} - 1) + \epsilon * x` .
     Arguments:
         - x: (:obj:`torch.Tensor`) The input tensor to be normalized.
         - eps: (:obj:`float`) The coefficient of the additive regularization term \
-            to ensure h^{-1} is Lipschitz continuous
+            to ensure inverse function is Lipschitz continuous
     Returns:
         - (:obj:`torch.Tensor`) Normalized tensor.
 
@@ -23,11 +23,11 @@ def value_inv_transform(x: torch.Tensor, eps: float = 1e-2) -> torch.Tensor:
     """
     Overview:
         The inverse form of value rescale.
-        :math: `h^{-1}(x) = sign(x)({(\frac{\sqrt{1+4\eps(|x|+1+\eps)}-1}{2\eps})}^2-1)` .
+        :math: `h^{-1}(x) = sign(x)({(\frac{\sqrt{1+4\epsilon(|x|+1+\epsilon)}-1}{2\epsilon})}^2-1)` .
     Arguments:
         - x: (:obj:`torch.Tensor`) The input tensor to be unnormalized.
         - eps: (:obj:`float`) The coefficient of the additive regularization term \
-            to ensure h^{-1} is Lipschitz continuous
+            to ensure inverse function is Lipschitz continuous
     Returns:
         - (:obj:`torch.Tensor`) Unnormalized tensor.
     """
diff --git a/ding/torch_utils/network/gtrxl.py b/ding/torch_utils/network/gtrxl.py
@@ -167,8 +167,7 @@ def update(self, hidden_state: List[torch.Tensor]):
         """
         Overview:
             Update the memory given a sequence of hidden states.
-            Example for single layer:
-                memory_len=3, hidden_size_len=2, bs=3
+            Example for single layer: (memory_len=3, hidden_size_len=2, bs=3)
 
                     m00 m01 m02      h00 h01 h02              m20 m21 m22
                 m = m10 m11 m12  h = h10 h11 h12  => new_m =  h00 h01 h02
@@ -264,9 +263,8 @@ def _rel_shift(self, x: torch.Tensor, zero_upper: bool = False) -> torch.Tensor:
                 4) Mask out the upper triangle (optional)
 
         .. note::
-            See the following material for better understanding:
-                https://github.com/kimiyoung/transformer-xl/issues/8
-                https://arxiv.org/pdf/1901.02860.pdf (Appendix B)
+            See the following material for better understanding: https://github.com/kimiyoung/transformer-xl/issues/8 \
+            https://arxiv.org/pdf/1901.02860.pdf (Appendix B)
         Arguments:
             - x (:obj:`torch.Tensor`): The input tensor with shape (cur_seq, full_seq, bs, head_num).
             - zero_upper (:obj:`bool`): If True, the upper-right triangle of the matrix is set to zero.
