update parl.maddpg without import gym (#208)

* add maddpg example

* format with yapf

* fix coding style

* fix coding style

* unittest without import multiagent env

* update maddpg code

* update maddpg readme

* add copyright comments

* update parl.maddpg without import gym

* update NeurlIPS2018.gif to NeurlIPS2019.gif

* update readme and comments

README.cn.md

@@ -82,6 +82,6 @@ pip install parl
 - [冠军解决方案：NIPS2018强化学习假肢挑战赛](examples/NeurIPS2018-AI-for-Prosthetics-Challenge/)
 - [冠军解决方案：NIPS2019强化学习仿生人控制赛事](examples/NeurIPS2019-Learn-to-Move-Challenge/)
 
-<img src=".github/NeurlIPS2018.gif" width = "300" height ="200" alt="NeurlIPS2018"/> <img src=".github/Half-Cheetah.gif" width = "300" height ="200" alt="Half-Cheetah"/> <img src=".github/Breakout.gif" width = "200" height ="200" alt="Breakout"/> 
+<img src="examples/NeurIPS2019-Learn-to-Move-Challenge/image/performance.gif" width = "300" height ="200" alt="NeurlIPS2018"/> <img src=".github/Half-Cheetah.gif" width = "300" height ="200" alt="Half-Cheetah"/> <img src=".github/Breakout.gif" width = "200" height ="200" alt="Breakout"/> 
 <br>
 <img src=".github/Aircraft.gif"  width = "808" height ="300"  alt="NeurlIPS2018"/>

README.md

@@ -85,6 +85,6 @@ pip install parl
 - [Winning Solution for NIPS2018: AI for Prosthetics Challenge](examples/NeurIPS2018-AI-for-Prosthetics-Challenge/)
 - [Winning Solution for NIPS2019: Learn to Move Challenge](examples/NeurIPS2019-Learn-to-Move-Challenge/)
 
-<img src=".github/NeurlIPS2018.gif" width = "300" height ="200" alt="NeurlIPS2018"/> <img src=".github/Half-Cheetah.gif" width = "300" height ="200" alt="Half-Cheetah"/> <img src=".github/Breakout.gif" width = "200" height ="200" alt="Breakout"/>
+<img src="examples/NeurIPS2019-Learn-to-Move-Challenge/image/performance.gif" width = "300" height ="200" alt="NeurlIPS2018"/> <img src=".github/Half-Cheetah.gif" width = "300" height ="200" alt="Half-Cheetah"/> <img src=".github/Breakout.gif" width = "200" height ="200" alt="Breakout"/>
 <br>
 <img src=".github/Aircraft.gif"  width = "808" height ="300"  alt="NeurlIPS2018"/>

parl/algorithms/fluid/maddpg.py

@@ -22,20 +22,27 @@ from parl.core.fluid.algorithm import Algorithm
 
 __all__ = ['MADDPG']
 
-from gym import spaces
 from parl.core.fluid.policy_distribution import SoftCategoricalDistribution
 from parl.core.fluid.policy_distribution import SoftMultiCategoricalDistribution
 
 
 def SoftPDistribution(logits, act_space):
-    if (isinstance(act_space, spaces.Discrete)):
+    """input:
+            logits: the output of policy model
+            act_space: action space, must be gym.spaces.Discrete or multiagent.multi_discrete.MultiDiscrete
+        output：
+            instance of SoftCategoricalDistribution or SoftMultiCategoricalDistribution
+    """
+    # is instance of gym.spaces.Discrete
+    if (hasattr(act_space, 'n')):
         return SoftCategoricalDistribution(logits)
     # is instance of multiagent.multi_discrete.MultiDiscrete
     elif (hasattr(act_space, 'num_discrete_space')):
         return SoftMultiCategoricalDistribution(logits, act_space.low,
                                                 act_space.high)
     else:
-        raise NotImplementedError
+        raise AssertionError("act_space must be instance of \
+            gym.spaces.Discrete or multiagent.multi_discrete.MultiDiscrete")
 
 
 class MADDPG(Algorithm):