Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Support
Keyboard shortcuts
?
Submit feedback
Sign in / Register
Toggle navigation
Y
ygo-agent
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Locked Files
Issues
0
Issues
0
List
Boards
Labels
Service Desk
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Security & Compliance
Security & Compliance
Dependency List
License Compliance
Packages
Packages
List
Container Registry
Analytics
Analytics
CI / CD
Code Review
Insights
Issues
Repository
Value Stream
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
Biluo Shen
ygo-agent
Commits
598465e8
Commit
598465e8
authored
Feb 25, 2024
by
biluo.shen
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
reduce_gradient out compile
parent
0559e98c
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
1 addition
and
1 deletion
+1
-1
scripts/ppo.py
scripts/ppo.py
+1
-1
No files found.
scripts/ppo.py
View file @
598465e8
...
@@ -267,7 +267,6 @@ def run(local_rank, world_size):
...
@@ -267,7 +267,6 @@ def run(local_rank, world_size):
optimizer
.
zero_grad
()
optimizer
.
zero_grad
()
scaler
.
scale
(
loss
)
.
backward
()
scaler
.
scale
(
loss
)
.
backward
()
scaler
.
unscale_
(
optimizer
)
scaler
.
unscale_
(
optimizer
)
reduce_gradidents
(
agent
,
args
.
world_size
)
return
old_approx_kl
,
approx_kl
,
clipfrac
,
pg_loss
,
v_loss
,
entropy_loss
return
old_approx_kl
,
approx_kl
,
clipfrac
,
pg_loss
,
v_loss
,
entropy_loss
def
predict_step
(
agent
,
next_obs
):
def
predict_step
(
agent
,
next_obs
):
...
@@ -403,6 +402,7 @@ def run(local_rank, world_size):
...
@@ -403,6 +402,7 @@ def run(local_rank, world_size):
old_approx_kl
,
approx_kl
,
clipfrac
,
pg_loss
,
v_loss
,
entropy_loss
=
\
old_approx_kl
,
approx_kl
,
clipfrac
,
pg_loss
,
v_loss
,
entropy_loss
=
\
train_step
(
agent
,
scaler
,
mb_obs
,
b_actions
[
mb_inds
],
b_logprobs
[
mb_inds
],
b_advantages
[
mb_inds
],
train_step
(
agent
,
scaler
,
mb_obs
,
b_actions
[
mb_inds
],
b_logprobs
[
mb_inds
],
b_advantages
[
mb_inds
],
b_returns
[
mb_inds
],
b_values
[
mb_inds
])
b_returns
[
mb_inds
],
b_values
[
mb_inds
])
reduce_gradidents
(
agent
,
args
.
world_size
)
nn
.
utils
.
clip_grad_norm_
(
agent
.
parameters
(),
args
.
max_grad_norm
)
nn
.
utils
.
clip_grad_norm_
(
agent
.
parameters
(),
args
.
max_grad_norm
)
scaler
.
step
(
optimizer
)
scaler
.
step
(
optimizer
)
scaler
.
update
()
scaler
.
update
()
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment