update to CartPoleBulletEnv-v1 and check with latest baselines v0.1.5, works fine.

(make it more similar to classical control cartpole)

examples/pybullet/gym/pybullet_data/cartpole.urdf

@@ -59,9 +59,15 @@
     </visual>
     <inertial>
     <origin xyz="0 0 0.5"/>
-      <mass value="10"/>
+      <mass value="0.1"/>
       <inertia ixx="1.0" ixy="0.0" ixz="0.0" iyy="1.0" iyz="0.0" izz="1.0"/>
     </inertial>
+<collision>
+      <geometry>
+        <box size="0.05 0.05 1.0"/>
+      </geometry>
+      <origin rpy="0 0 0" xyz="0 0 0.5"/>
+    </collision>
   </link>
 
   <joint name="cart_to_pole" type="continuous">