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

minor fix

Browse Source
This commit is contained in:
Haosheng Zou 2017-12-14 19:46:38 +08:00
parent 039c8140e2
commit 92deae9f8d
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
examples/dqn_example.py
View File

@ -53,7 +53,7 @@ if __name__ == '__main__':
action = tf.placeholder(dtype=tf.int32, shape=[None]) # batch of integer actions action = tf.placeholder(dtype=tf.int32, shape=[None]) # batch of integer actions
target = tf.placeholder(dtype=tf.float32, shape=[None]) # target value for DQN target = tf.placeholder(dtype=tf.float32, shape=[None]) # target value for DQN
dqn_loss = losses.dqn_loss(action, target, pi) # TongzhengRen dqn_loss = losses.dqn_loss(action, target, q_net) # TongzhengRen
total_loss = dqn_loss total_loss = dqn_loss
optimizer = tf.train.AdamOptimizer(1e-3) optimizer = tf.train.AdamOptimizer(1e-3)
@ -61,7 +61,7 @@ if __name__ == '__main__':
# 3. define data collection # 3. define data collection
training_data = Replay(env, q_net, advantage_estimation.qlearning_target(target_net)) # training_data = Replay(env, q_net, advantage_estimation.qlearning_target(target_net)) #
# ShihongSong: Replay(env, pi, advantage_estimation.qlearning_target(target_network)), use your ReplayMemory, interact as follows. Simplify your advantage_estimation.dqn to run before YongRen's DQN # ShihongSong: Replay(env, q_net, advantage_estimation.qlearning_target(target_network)), use your ReplayMemory, interact as follows. Simplify your advantage_estimation.dqn to run before YongRen's DQN
# maybe a dict to manage the elements to be collected # maybe a dict to manage the elements to be collected
# 4. start training # 4. start training