mirror of
https://github.com/vale981/ray
synced 2025-03-06 10:31:39 -05:00

* Fix. * Rollback. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * Fix. * Fix. * Fix. * Fix. * Fix. * WIP. * WIP. * Fix. * Test case fixes. * Test case fixes and LINT. * Test case fixes and LINT. * Rollback. * WIP. * WIP. * Test case fixes. * Fix. * Fix. * Fix. * Add regression test for DQN w/ param noise. * Fixes and LINT. * Fixes and LINT. * Fixes and LINT. * Fixes and LINT. * Fixes and LINT. * Comment * Regression test case. * WIP. * WIP. * LINT. * LINT. * WIP. * Fix. * Fix. * Fix. * LINT. * Fix (SAC does currently not support eager). * Fix. * WIP. * LINT. * Update rllib/evaluation/sampler.py Co-Authored-By: Eric Liang <ekhliang@gmail.com> * Update rllib/evaluation/sampler.py Co-Authored-By: Eric Liang <ekhliang@gmail.com> * Update rllib/utils/exploration/exploration.py Co-Authored-By: Eric Liang <ekhliang@gmail.com> * Update rllib/utils/exploration/exploration.py Co-Authored-By: Eric Liang <ekhliang@gmail.com> * WIP. * WIP. * Fix. * LINT. * LINT. * Fix and LINT. * WIP. * WIP. * WIP. * WIP. * Fix. * LINT. * Fix. * Fix and LINT. * Update rllib/utils/exploration/exploration.py * Update rllib/policy/dynamic_tf_policy.py Co-Authored-By: Eric Liang <ekhliang@gmail.com> * Update rllib/policy/dynamic_tf_policy.py Co-Authored-By: Eric Liang <ekhliang@gmail.com> * Update rllib/policy/dynamic_tf_policy.py Co-Authored-By: Eric Liang <ekhliang@gmail.com> * Fixes. * WIP. * LINT. * Fixes and LINT. * LINT and fixes. * LINT. * Move action_dist back into torch extra_action_out_fn and LINT. * Working SimpleQ learning cartpole on both torch AND tf. * Working Rainbow learning cartpole on tf. * Working Rainbow learning cartpole on tf. * WIP. * LINT. * LINT. * Update docs and add torch to APEX test. * LINT. * Fix. * LINT. * Fix. * Fix. * Fix and docstrings. * Fix broken RLlib tests in master. * Split BAZEL learning tests into cartpole and pendulum (reached the 60min barrier). * Fix error_outputs option in BAZEL for RLlib regression tests. * Fix. * Tune param-noise tests. * LINT. * Fix. * Fix. * test * test * test * Fix. * Fix. * WIP. * WIP. * WIP. * WIP. * LINT. * WIP. Co-authored-by: Eric Liang <ekhliang@gmail.com>
101 lines
2.9 KiB
Python
101 lines
2.9 KiB
Python
from functools import partial
|
|
|
|
from ray.rllib.utils.annotations import override, PublicAPI, DeveloperAPI
|
|
from ray.rllib.utils.framework import try_import_tf, try_import_tfp, \
|
|
try_import_torch, check_framework
|
|
from ray.rllib.utils.deprecation import deprecation_warning, renamed_agent, \
|
|
renamed_class, renamed_function
|
|
from ray.rllib.utils.filter_manager import FilterManager
|
|
from ray.rllib.utils.filter import Filter
|
|
from ray.rllib.utils.numpy import sigmoid, softmax, relu, one_hot, fc, lstm, \
|
|
SMALL_NUMBER, LARGE_INTEGER, MIN_LOG_NN_OUTPUT, MAX_LOG_NN_OUTPUT
|
|
from ray.rllib.utils.policy_client import PolicyClient
|
|
from ray.rllib.utils.policy_server import PolicyServer
|
|
from ray.rllib.utils.schedules import LinearSchedule, PiecewiseSchedule, \
|
|
PolynomialSchedule, ExponentialSchedule, ConstantSchedule
|
|
from ray.rllib.utils.test_utils import check, framework_iterator
|
|
from ray.rllib.utils.torch_ops import convert_to_non_torch_type, \
|
|
convert_to_torch_tensor
|
|
from ray.tune.utils import merge_dicts, deep_update
|
|
|
|
|
|
def add_mixins(base, mixins):
|
|
"""Returns a new class with mixins applied in priority order."""
|
|
|
|
mixins = list(mixins or [])
|
|
|
|
while mixins:
|
|
|
|
class new_base(mixins.pop(), base):
|
|
pass
|
|
|
|
base = new_base
|
|
|
|
return base
|
|
|
|
|
|
def force_list(elements=None, to_tuple=False):
|
|
"""
|
|
Makes sure `elements` is returned as a list, whether `elements` is a single
|
|
item, already a list, or a tuple.
|
|
|
|
Args:
|
|
elements (Optional[any]): The inputs as single item, list, or tuple to
|
|
be converted into a list/tuple. If None, returns empty list/tuple.
|
|
to_tuple (bool): Whether to use tuple (instead of list).
|
|
|
|
Returns:
|
|
Union[list,tuple]: All given elements in a list/tuple depending on
|
|
`to_tuple`'s value. If elements is None,
|
|
returns an empty list/tuple.
|
|
"""
|
|
ctor = list
|
|
if to_tuple is True:
|
|
ctor = tuple
|
|
return ctor() if elements is None else ctor(elements) \
|
|
if type(elements) in [list, tuple] else ctor([elements])
|
|
|
|
|
|
force_tuple = partial(force_list, to_tuple=True)
|
|
|
|
__all__ = [
|
|
"add_mixins",
|
|
"check",
|
|
"check_framework",
|
|
"convert_to_non_torch_type",
|
|
"convert_to_torch_tensor",
|
|
"deprecation_warning",
|
|
"fc",
|
|
"force_list",
|
|
"force_tuple",
|
|
"framework_iterator",
|
|
"lstm",
|
|
"one_hot",
|
|
"relu",
|
|
"sigmoid",
|
|
"softmax",
|
|
"deep_update",
|
|
"merge_dicts",
|
|
"override",
|
|
"renamed_function",
|
|
"renamed_agent",
|
|
"renamed_class",
|
|
"try_import_tf",
|
|
"try_import_tfp",
|
|
"try_import_torch",
|
|
"ConstantSchedule",
|
|
"DeveloperAPI",
|
|
"ExponentialSchedule",
|
|
"Filter",
|
|
"FilterManager",
|
|
"LARGE_INTEGER",
|
|
"LinearSchedule",
|
|
"MAX_LOG_NN_OUTPUT",
|
|
"MIN_LOG_NN_OUTPUT",
|
|
"PiecewiseSchedule",
|
|
"PolicyClient",
|
|
"PolicyServer",
|
|
"PolynomialSchedule",
|
|
"PublicAPI",
|
|
"SMALL_NUMBER",
|
|
]
|