Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[rllib] Initial work on integrating hyperparameter search tool #1107

Merged
merged 17 commits into from
Oct 13, 2017
Merged

[rllib] Initial work on integrating hyperparameter search tool #1107

Changes from 1 commit
Commits
Show all changes
17 commits
Select commit Hold shift + click to select a range
26c54e7
clean up train
ericl Oct 10, 2017
4ba055a
update
ericl Oct 10, 2017
98366ba
update train script
ericl Oct 11, 2017
9db66a8
add tuned examples
ericl Oct 11, 2017
c65c379
add agent catalog
ericl Oct 11, 2017
dde75b5
add tune lib
ericl Oct 11, 2017
c3fded2
update
ericl Oct 11, 2017
5c31f70
fix
ericl Oct 11, 2017
c457d66
testS
ericl Oct 11, 2017
bfd7c94
remove
ericl Oct 11, 2017
54b196f
train docs
ericl Oct 11, 2017
fbbd9f0
comments
ericl Oct 12, 2017
81ad34f
todo
ericl Oct 12, 2017
81dfd3e
fix resource parsing
ericl Oct 12, 2017
42186b2
fix cr test
ericl Oct 12, 2017
865007f
add test
ericl Oct 13, 2017
4995ae2
try to fix travis test
ericl Oct 13, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
todo
  • Loading branch information
@ericl
ericl committed Oct 12, 2017
commit 81ad34f8f0118d8f7e37ab639c36cff3724eec00
11 changes: 8 additions & 3 deletions python/ray/tune/README.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,11 +1,11 @@
ray.tune: fast hyperparameter search
Ray.tune: Fast hyperparameter search
====================================

Using ray.tune with RLlib
-------------------------

You can use ray.tune through RLlib's train.py script. The train.py script
supports two modes:
One way to use ray.tune is through RLlib's train.py script. The train.py script
supports two modes. For example, to run multiple concurrent trials of Pong:

- Inline args: ``./train.py --env=Pong-v0 --alg=PPO --num_trials=8 --stop '{"time_total_s": 3200}' --resources '{"cpu": 8, "gpu": 2}' --config '{"num_workers": 8, "sgd_num_iter": 10}'``

Expand Down Expand Up @@ -47,3 +47,8 @@ Using ray.tune to run custom scripts
------------------------------------

TODO

Using ray.tune as a library
---------------------------

TODO