-
Notifications
You must be signed in to change notification settings - Fork 6k
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] Make Episode.to_numpy
optional at end of EnvRunner.sample()
(renamed from finalize()
).
#49800
[RLlib] Make Episode.to_numpy
optional at end of EnvRunner.sample()
(renamed from finalize()
).
#49800
Conversation
…ot_finalize_episodes_sent_to_buffer
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. I like this new naming. Imo it tells more clearly what we do there. One thing: Could you check the OfflinePreLearner
and see, if there the finalize
needs to be changed as well?
rllib/algorithms/algorithm_config.py
Outdated
@@ -325,6 +325,7 @@ def __init__(self, algo_class: Optional[type] = None): | |||
self.num_gpus_per_env_runner = 0 | |||
self.custom_resources_per_env_runner = {} | |||
self.validate_env_runners_after_construction = True | |||
self.episodes_to_numpy = False |
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.
Nice!
I think I went through all the code. But let me check again ... |
Ah, yeah, fixed it in the docs ... |
…ot_finalize_episodes_sent_to_buffer
…_accelerate Signed-off-by: sven1977 <svenmika1977@gmail.com> # Conflicts: # rllib/algorithms/algorithm_config.py
…ot_finalize_episodes_sent_to_buffer Signed-off-by: sven1977 <svenmika1977@gmail.com> # Conflicts: # rllib/utils/replay_buffers/episode_replay_buffer.py
…ot_finalize_episodes_sent_to_buffer
…)` (renamed from `finalize()`). (#49800)
…)` (renamed from `finalize()`). (ray-project#49800) Signed-off-by: Puyuan Yao <williamyao034@gmail.com>
Make
Episode.to_numpy()
optional at end ofEnvRunner.sample()
(renamed fromfinalize()
).Episode.finalize()
->to_numpy()
; RenamedEpisode.is_finalized
->is_numpy
.EnvRunner.sample()
in list format, instead of numpy'izing (fka: finalizing) them.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.