Tensorflow one_hot
```python indices = [0, 1, 2] depth = 3 tf.one_hot(indices, depth) # output: [3 x 3] [[1., 0., 0.], [0., 1., 0.], [0., 0., 1.]]
```python indices = [0, 1, 2] depth = 3 tf.one_hot(indices, depth) # output: [3 x 3] [[1., 0., 0.], [0., 1., 0.], [0., 0., 1.]]
```python tf.gather( params, indices, validate_indices=None, name=None, axis=0 )
```python tf.expand_dims( input, axis=None, name=None, dim=None )
itertools API First, let’s get the boring part out of the way: ```python import itertools
Understand Memory Augmented Reinforcement Learning Can we learn an agent with an external memory? external memory (Read/Write)