hongshaorou/Tianshou
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

add some TODO

Browse Source
This commit is contained in:
rtz19970824 2017-12-10 13:31:43 +08:00
parent ec6114edf1
commit 18b3b0b850
2 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@ -44,6 +44,9 @@ Tianshou(天授) is a reinforcement learning platform. The following image illus
## TODO ## TODO
Search based method parallel. Search based method parallel.
<font color=Red> Write comments. Please do not use abbreviations unless others can know it well. (e.g. adv can short for advantage/adversarial, please use the full name instead) </font>
<font color=Red> Please name the module formally. (e.g. use more lower case "_", I think a module called "Batch" seems terrible)</font>
YongRen: Policy Wrapper, in order of Gaussian, DQN and DDPG YongRen: Policy Wrapper, in order of Gaussian, DQN and DDPG
TongzhengRen: losses, in order of ppo, pg, DQN, DDPG with management of placeholders TongzhengRen: losses, in order of ppo, pg, DQN, DDPG with management of placeholders

1
tianshou/data/Batch.py
View File

@ -2,6 +2,7 @@ import numpy as np
import gc import gc
# TODO: Refactor with tf.train.slice_input_producer, tf.train.Coordinator, tf.train.QueueRunner
class Batch(object): class Batch(object):
""" """
class for batch datasets. Collect multiple states (actions, rewards, etc.) on-policy. class for batch datasets. Collect multiple states (actions, rewards, etc.) on-policy.