update docs urls (pyro-ppl#1757)

pyro/contrib/minipyro.py

@@ -20,9 +20,9 @@
 # Pyro keeps track of two kinds of global state:
 # i)  The effect handler stack, which enables non-standard interpretations of
 #     Pyro primitives like sample();
-#     See http://docs.pyro.ai/en/0.3.0-release/poutine.html
+#     See http://docs.pyro.ai/en/0.3.1/poutine.html
 # ii) Trainable parameters in the Pyro ParamStore;
-#     See http://docs.pyro.ai/en/0.3.0-release/parameters.html
+#     See http://docs.pyro.ai/en/0.3.1/parameters.html
 
 PYRO_STACK = []
 PARAM_STORE = {}
@@ -201,7 +201,7 @@ def plate(name, size, dim):
 
 # This is a thin wrapper around the `torch.optim.Adam` class that
 # dynamically generates optimizers for dynamically generated parameters.
-# See http://docs.pyro.ai/en/0.3.0-release/optimization.html
+# See http://docs.pyro.ai/en/0.3.1/optimization.html
 class Adam(object):
     def __init__(self, optim_args):
         self.optim_args = optim_args
@@ -226,7 +226,7 @@ def __call__(self, params):
 
 # This is a unified interface for stochastic variational inference in Pyro.
 # The actual construction of the loss is taken care of by `loss`.
-# See http://docs.pyro.ai/en/0.3.0-release/inference_algos.html
+# See http://docs.pyro.ai/en/0.3.1/inference_algos.html
 class SVI(object):
     def __init__(self, model, guide, optim, loss):
         self.model = model

tutorial/source/bo.ipynb

@@ -35,7 +35,7 @@
     "\n",
     "A good acquisition function should make use of the uncertainty encoded in the posterior to encourage a balance between exploration—querying points where we know little about $f$—and exploitation—querying points in regions we have good reason to think $x^*$ may lie. As the iterative procedure progresses our model for $f$ evolves and so does the acquisition function. If our model is good and we've chosen a reasonable acquisition function, we expect that the acquisition function will guide the query points $x_n$ towards $x^*$.\n",
     "\n",
-    "In this tutorial, our model for $f$ will be a Gaussian process. In particular we will see how to use the [Gaussian Process module](http://docs.pyro.ai/en/0.2.0-release/contrib.gp.html) in Pyro to implement a simple Bayesian optimization procedure."
+    "In this tutorial, our model for $f$ will be a Gaussian process. In particular we will see how to use the [Gaussian Process module](http://docs.pyro.ai/en/0.3.1/contrib.gp.html) in Pyro to implement a simple Bayesian optimization procedure."
    ]
   },
   {