-
Notifications
You must be signed in to change notification settings - Fork 5.3k
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.
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] AlgorithmConfig cleanup 02: Restructure methods and properties. #44896
[RLlib] AlgorithmConfig cleanup 02: Restructure methods and properties. #44896
Conversation
…rithm_config_cleanup_02_restructure_methods Signed-off-by: sven1977 <svenmika1977@gmail.com> # Conflicts: # rllib/examples/evaluation/evaluation_parallel_to_training.py
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM. Small changes but a lot of them.
@@ -29,7 +29,7 @@ def get(self): | |||
# __rllib-adv_api_explore_begin__ | |||
from ray.rllib.algorithms.algorithm_config import AlgorithmConfig | |||
|
|||
config = AlgorithmConfig().exploration( |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Isn't rollout a typically used name in RL for rolling out the policy for sampling?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Totally, but I felt like some of these settings in here are less concerned about the rollout process itself, but more about how the EnvRunner (that performs these rollouts) is set up. Let me think about it again a bit ...
AlgorithmConfig cleanup 02: Restructure methods and properties:
rollouts()
intoenv_runners()
.exploration()
intoenv_runners(explore=.., exploration_config=..)
.num_rollout_workers
->num_env_runners
,num_envs_per_worker
->num_envs_per_env_runner
, etc..\@OldAPIStack
.Why are these changes needed?
Related issue number
Checks
git commit -s
) in this PR.scripts/format.sh
to lint the changes in this PR.method in Tune, I've added it in
doc/source/tune/api/
under thecorresponding
.rst
file.