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

Change action_dim to action_shape (#602)

Browse Source 
Noticed that in IQN and FQF there were some mismatches in the docstrings. Figured I would make a pull request to make it match.
This commit is contained in:
Squeemos 2022-04-21 17:09:57 -07:00 committed by GitHub
parent 57ecebde38
commit e01385ea30
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
tianshou/utils/net/discrete.py
View File

@ -160,7 +160,7 @@ class ImplicitQuantileNetwork(Critic):
:param preprocess_net: a self-defined preprocess_net which output a :param preprocess_net: a self-defined preprocess_net which output a
flattened hidden state. flattened hidden state.
:param int action_dim: the dimension of action space. :param int action_shape: a sequence of int for the shape of action.
:param hidden_sizes: a sequence of int for constructing the MLP after :param hidden_sizes: a sequence of int for constructing the MLP after
preprocess_net. Default to empty sequence (where the MLP now contains preprocess_net. Default to empty sequence (where the MLP now contains
only a single linear layer). only a single linear layer).
@ -254,7 +254,7 @@ class FullQuantileFunction(ImplicitQuantileNetwork):
:param preprocess_net: a self-defined preprocess_net which output a :param preprocess_net: a self-defined preprocess_net which output a
flattened hidden state. flattened hidden state.
:param int action_dim: the dimension of action space. :param int action_shape: a sequence of int for the shape of action.
:param hidden_sizes: a sequence of int for constructing the MLP after :param hidden_sizes: a sequence of int for constructing the MLP after
preprocess_net. Default to empty sequence (where the MLP now contains preprocess_net. Default to empty sequence (where the MLP now contains
only a single linear layer). only a single linear layer).