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

data/utils.py added but not pushed...

Browse Source
This commit is contained in:
haoshengzou 2018-01-25 10:11:36 +08:00
parent f32e1d9c12
commit 5910e08672
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tianshou/core/opt.py
View File

@ -15,6 +15,7 @@ def DPG(policy, action_value):
grad_ys = tf.gradients(critic_value_loss, critic_action_input)
grad_policy_vars = tf.gradients(policy_action_output, trainable_variables, grad_ys=grad_ys)
# TODO: this is slightly different from ddpg implementations in baselines, keras-rl and rllab. it uses sampled action (with noise) rather than directly connect the two networks
grads_and_vars = zip(grad_policy_vars, trainable_variables)