Skip to content

Commit

Permalink
Fix link to variable horizon article.
Browse files Browse the repository at this point in the history
  • Loading branch information
ernestum committed Sep 6, 2023
1 parent 5b0b531 commit cd9a470
Show file tree
Hide file tree
Showing 5 changed files with 10 additions and 10 deletions.
2 changes: 1 addition & 1 deletion src/imitation/algorithms/adversarial/common.py
Original file line number Diff line number Diff line change
Expand Up @@ -176,7 +176,7 @@ def __init__(
training. If True, overrides this safety check. WARNING: variable
horizon episodes leak information about the reward via termination
condition, and can seriously confound evaluation. Read
https://imitation.readthedocs.io/en/latest/guide/variable_horizon.html
https://imitation.readthedocs.io/en/latest/main-concepts/variable_horizon.html
before overriding this.
Raises:
Expand Down
12 changes: 6 additions & 6 deletions src/imitation/algorithms/base.py
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,7 @@ def __init__(
training. If True, overrides this safety check. WARNING: variable
horizon episodes leak information about the reward via termination
condition, and can seriously confound evaluation. Read
https://imitation.readthedocs.io/en/latest/getting-started/variable-horizon.html
https://imitation.readthedocs.io/en/latest/main-concepts/variable_horizon.html
before overriding this.
"""
self._logger = custom_logger or imit_logger.configure()
Expand All @@ -61,8 +61,8 @@ def __init__(
"Additionally, even unbiased algorithms can exploit "
"the information leak from the termination condition, "
"producing spuriously high performance. See "
"https://imitation.readthedocs.io/en/latest/getting-started/"
"variable-horizon.html for more information.",
"https://imitation.readthedocs.io/en/latest/main-concepts/"
"variable_horizon.html for more information.",
)
self._horizon = None

Expand Down Expand Up @@ -100,8 +100,8 @@ def _check_fixed_horizon(self, horizons: Iterable[int]) -> None:
f"Episodes of different length detected: {horizons}. "
"Variable horizon environments are discouraged -- "
"termination conditions leak information about reward. See "
"https://imitation.readthedocs.io/en/latest/getting-started/"
"variable-horizon.html for more information. "
"https://imitation.readthedocs.io/en/latest/main-concepts/"
"variable_horizon.html for more information. "
"If you are SURE you want to run imitation on a "
"variable horizon task, then please pass in the flag: "
"`allow_variable_horizon=True`.",
Expand Down Expand Up @@ -152,7 +152,7 @@ def __init__(
training. If True, overrides this safety check. WARNING: variable
horizon episodes leak information about the reward via termination
condition, and can seriously confound evaluation. Read
https://imitation.readthedocs.io/en/latest/getting-started/variable-horizon.html
https://imitation.readthedocs.io/en/latest/main-concepts/variable_horizon.html
before overriding this.
"""
super().__init__(
Expand Down
2 changes: 1 addition & 1 deletion src/imitation/algorithms/density.py
Original file line number Diff line number Diff line change
Expand Up @@ -104,7 +104,7 @@ def __init__(
training. If True, overrides this safety check. WARNING: variable
horizon episodes leak information about the reward via termination
condition, and can seriously confound evaluation. Read
https://imitation.readthedocs.io/en/latest/guide/variable_horizon.html
https://imitation.readthedocs.io/en/latest/main-concepts/variable_horizon.html
before overriding this.
"""
self.is_stationary = is_stationary
Expand Down
2 changes: 1 addition & 1 deletion src/imitation/algorithms/preference_comparisons.py
Original file line number Diff line number Diff line change
Expand Up @@ -1550,7 +1550,7 @@ def __init__(
training. If True, overrides this safety check. WARNING: variable
horizon episodes leak information about the reward via termination
condition, and can seriously confound evaluation. Read
https://imitation.readthedocs.io/en/latest/guide/variable_horizon.html
https://imitation.readthedocs.io/en/latest/main-concepts/variable_horizon.html
before overriding this.
rng: random number generator to use for initializing subcomponents such as
fragmenter.
Expand Down
2 changes: 1 addition & 1 deletion src/imitation/scripts/train_preference_comparisons.py
Original file line number Diff line number Diff line change
Expand Up @@ -133,7 +133,7 @@ def train_preference_comparisons(
training. If True, overrides this safety check. WARNING: variable
horizon episodes leak information about the reward via termination
condition, and can seriously confound evaluation. Read
https://imitation.readthedocs.io/en/latest/guide/variable_horizon.html
https://imitation.readthedocs.io/en/latest/main-concepts/variable_horizon.html
before overriding this.
checkpoint_interval: Save the reward model and policy models (if
trajectory_generator contains a policy) every `checkpoint_interval`
Expand Down

0 comments on commit cd9a470

Please sign in to comment.