gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-02-25 11:45:46 +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

4
rl_coach/memories/non_episodic/differentiable_neural_dictionary.py
View File

@@ -57,7 +57,7 @@ class AnnoyDictionary(object):
self.built_capacity = 0
def add(self, keys, values, additional_data=None):
def add(self, keys, values, additional_data=None, force_rebuild_tree=False):
if not additional_data:
additional_data = [None] * len(keys)
@@ -96,7 +96,7 @@ class AnnoyDictionary(object):
if len(self.buffered_indices) >= self.min_update_size:
self.min_update_size = max(self.initial_update_size, int(self.curr_size * 0.02))
self._rebuild_index()
elif self.rebuild_on_every_update:
elif force_rebuild_tree or self.rebuild_on_every_update:
self._rebuild_index()
self.current_timestamp += 1