hecong97

**Can I hide the agent in the top-down view of the maze?**  I want have a top-down map with only the goal,is that easy to implement?

I wonder to know how can I create placeholders like dnc_core.initial_state(batch_size=n) with the batch_size n changed in trainning. > dnc_core = dnc.DNC(...) > initial_core_state = dnc_core.initial_state(batch_size=1) > core_state_placeholders = snt.nest.map(lambda...