-
Notifications
You must be signed in to change notification settings - Fork 5.9k
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] Cleanup examples folder (new API stack) vol 31: Add hierarchical training example script. #49127
[RLlib] Cleanup examples folder (new API stack) vol 31: Add hierarchical training example script. #49127
Conversation
…nup_examples_folder_31_hierarchical_training
…nup_examples_folder_31_hierarchical_training
…nup_examples_folder_31_hierarchical_training
…nup_examples_folder_31_hierarchical_training
…nup_examples_folder_31_hierarchical_training
…nup_examples_folder_31_hierarchical_training
doc/source/rllib/rllib-examples.rst
Outdated
Hierarchical Training | ||
+++++++++++++++++++++ | ||
|
||
- `Policy Inference after Training <https://github.com/ray-project/ray/blob/master/rllib/examples/inference/policy_inference_after_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.
sorry, still WIP ... please ignore this change here for now
@@ -533,9 +533,18 @@ def _get_int_index( | |||
): | |||
data_to_use = self.data | |||
if _ignore_last_ts: | |||
data_to_use = self.data[:-1] | |||
if self.finalized: |
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.
these were all bugs
rllib/env/multi_agent_episode.py
Outdated
return { | ||
key: sub_buffer.get( | ||
indices=index_incl_lookback - sub_buffer.lookback, | ||
neg_index_as_lookback=True, | ||
fill=fill, | ||
_add_last_ts_value=hanging_val, | ||
_add_last_ts_value=( |
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.
another bug fix
…nup_examples_folder_31_hierarchical_training
…xamples_folder_31_hierarchical_training # Conflicts: # rllib/env/multi_agent_episode.py # rllib/env/single_agent_episode.py # rllib/env/tests/test_multi_agent_episode.py # rllib/env/utils/infinite_lookback_buffer.py
Signed-off-by: sven1977 <svenmika1977@gmail.com>
…nup_examples_folder_31_hierarchical_training Signed-off-by: sven1977 <svenmika1977@gmail.com> # Conflicts: # rllib/env/multi_agent_episode.py
…cal training example script. (ray-project#49127)
…cal training example script. (ray-project#49127) Signed-off-by: ujjawal-khare <ujjawal.khare@dream11.com>
Cleanup examples folder (new API stack) vol 31:
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.