Commit 1f913dc3 authored by Jae Young Lee's avatar Jae Young Lee

A TODO added to

parent c3e0e738
......@@ -52,6 +52,8 @@ class ControllerBase(PolicyBase):
Returns state at end of node execution, total reward, epsiode_termination_flag, info
# TODO: this is never called when you TEST high-level policy (w/o MCTS) rather than train...
# (make some integrated interface btw testing and training and b.t.w. the high- and low-level
# methods with and without MCTS.
def step_current_node(self, visualize_low_level_steps=False):
total_reward = 0
self.node_terminal_state_reached = False
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment