From b40f26bab162789d29305028347f06ea339ea3c7 Mon Sep 17 00:00:00 2001
From: baijinqiu <2522827873@qq.com>
Date: Mon, 25 Dec 2023 14:37:13 +0800
Subject: [PATCH] 'iddpg_learner_x(#1)'

---
 .../documents/api/learners/marl/iddpg.rst     | 30 +++++++++++--------
 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/docs/source/documents/api/learners/marl/iddpg.rst b/docs/source/documents/api/learners/marl/iddpg.rst
index d574bc60..c0fdfe51 100644
--- a/docs/source/documents/api/learners/marl/iddpg.rst
+++ b/docs/source/documents/api/learners/marl/iddpg.rst
@@ -1,7 +1,7 @@
 IDDPG_Learner
 =====================================
 
-xxxxxx.
+An Independent Deep Deterministic Policy Gradient (IDDPG) learner.
 
 .. raw:: html
 
@@ -33,10 +33,12 @@ PyTorch
 .. py:function::
   xuance.torch.learners.multi_agent_rl.iddpg_learner.IDDPG_Learner.update(sample)
 
-  xxxxxx.
+  Update the IDDPG learner with a batch of samples.
 
-  :param sample: xxxxxx.
-  :type sample: xxxxxx
+  :param sample: A dictionary containing current observations, actions taken in the current state,
+                    observations of the next state, rewards, binary indicators of episode terminations,
+                    binary mask indicating which agents are active.
+  :type sample: dict
   :return: The infomation of the training.
   :rtype: dict
 
@@ -70,11 +72,13 @@ TensorFlow
 .. py:function::
   xuance.tensorflow.learners.multi_agent_rl.iddpg_learner.IDDPG_Learner.update(sample)
 
-  xxxxxx.
+  Update the IDDPG learner with a batch of samples.
 
-  :param sample: xxxxxx.
-  :type sample: xxxxxx
-  :return: The infomation of the training.
+  :param sample: A dictionary containing current observations, actions taken in the current state,
+                    observations of the next state, rewards, binary indicators of episode terminations,
+                    binary mask indicating which agents are active.
+  :type sample: dict
+  :return: The information of the training.
   :rtype: dict
 
 .. raw:: html
@@ -105,11 +109,13 @@ MindSpore
 .. py:function::
   xuance.mindspore.learners.multi_agent_rl.iddpg_learner.IDDPG_Learner.update(sample)
 
-  xxxxxx.
+  Update the IDDPG learner with a batch of samples.
 
-  :param sample: xxxxxx.
-  :type sample: xxxxxx
-  :return: The infomation of the training.
+  :param sample: A dictionary containing current observations, actions taken in the current state,
+                    observations of the next state, rewards, binary indicators of episode terminations,
+                    binary mask indicating which agents are active.
+  :type sample: dict
+  :return: The information of the training.
   :rtype: dict
 
 .. raw:: html