gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-18 11:40:18 +01:00
Code Issues Projects Releases Wiki Activity

RL in Large Discrete Action Spaces - Wolpertinger Agent (#394)

Browse Source 
* Currently this is specific to the case of discretizing a continuous action space. Can easily be adapted to other case by feeding the kNN otherwise, and removing the usage of a discretizing output action filter
This commit is contained in:
Gal Leibovich
2019-09-08 12:53:49 +03:00
committed by GitHub
parent fc50398544
commit 138ced23ba
46 changed files with 1193 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
rl_coach/filters/action/partial_discrete_action_space_map.py
View File

@@ -48,7 +48,8 @@ class PartialDiscreteActionSpaceMap(ActionFilter):
def get_unfiltered_action_space(self, output_action_space: ActionSpace) -> DiscreteActionSpace:
self.output_action_space = output_action_space
self.input_action_space = DiscreteActionSpace(len(self.target_actions), self.descriptions)
self.input_action_space = DiscreteActionSpace(len(self.target_actions), self.descriptions,
filtered_action_space=output_action_space)
return self.input_action_space
def filter(self, action: ActionType) -> ActionType: