fix docs

docs/index.rst

@@ -50,7 +50,7 @@ Tianshou is still under development, you can also check out the documents in sta
 
    tutorials/dqn
    tutorials/concepts
-   tutorials/tabular
+   tutorials/trick
    tutorials/cheatsheet
 
 .. toctree::

docs/tutorials/dqn.rst

@@ -211,7 +211,7 @@ No problem! Tianshou supports user-defined training code. Here is the usage:
         # train policy with a sampled batch data
         losses = policy.learn(train_collector.sample(batch_size=64))
 
-For further usage, you can refer to :doc:`/tutorials/tabular`.
+For further usage, you can refer to :doc:`/tutorials/cheatsheet`.
 
 .. rubric:: References
 

tianshou/policy/base.py

@@ -30,8 +30,8 @@ class BasePolicy(ABC, nn.Module):
         the network might be ``(mu, sigma), state`` for Gaussian policy.
 
     Since :class:`~tianshou.policy.BasePolicy` inherits ``torch.nn.Module``,
-    you can operate :class:`~tianshou.policy.BasePolicy` almost the same as
+    you can use :class:`~tianshou.policy.BasePolicy` almost the same as
-    ``torch.nn.Module``, for instance, load and save the model:
+    ``torch.nn.Module``, for instance, loading and saving the model:
     ::
 
         torch.save(policy.state_dict(), 'policy.pth')