gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-17 11:10:20 +01:00
Code Issues Projects Releases Wiki Activity

Cleanup and refactoring (#171)

Browse Source
This commit is contained in:
Zach Dwiel
2019-01-15 03:04:53 -05:00
committed by Gal Leibovich
parent cd812b0d25
commit fedb4cbd7c
7 changed files with 45 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
rl_coach/agents/dfp_agent.py
View File

@@ -84,7 +84,8 @@ class DFPAlgorithmParameters(AlgorithmParameters):
"""
:param num_predicted_steps_ahead: (int)
Number of future steps to predict measurements for. The future steps won't be sequential, but rather jump
in multiples of 2. For example, if num_predicted_steps_ahead = 3, then the steps will be: t+1, t+2, t+4
in multiples of 2. For example, if num_predicted_steps_ahead = 3, then the steps will be: t+1, t+2, t+4.
The predicted steps will be [t + 2**i for i in range(num_predicted_steps_ahead)]
:param goal_vector: (List[float])
The goal vector will weight each of the measurements to form an optimization goal. The vector should have