mirror of
https://github.com/wassname/ray.git
synced 2026-07-08 18:08:36 +08:00
Eric Liang
6cb5b90bd6
* dynamic graph * wip * clean up * fix * document trainer * wip * initialize the graph using a fake batch * clean up dynamic init * wip * spelling * use builder for ppo pol graph * add ppo graph * fix naming * order * docs * set class name correctly * add torch builder * add custom model support in builder * cleanup * remove underscores * fix py2 compat * Update dynamic_tf_policy_graph.py * Update tracking_dict.py * wip * rename * debug level * rename policy_graph -> policy in new classes * fix test * rename ppo tf policy * port appo too * forgot grads * default policy optimizer * make default config optional * add config to optimizer * use lr by default in optimizer * update * comments * remove optimizer * fix tuple actions support in dynamic tf graph
36 lines
904 B
Python
36 lines
904 B
Python
from __future__ import absolute_import
|
|
from __future__ import division
|
|
from __future__ import print_function
|
|
|
|
from ray.rllib.agents.trainer import with_common_config
|
|
from ray.rllib.agents.trainer_template import build_trainer
|
|
from ray.rllib.agents.pg.pg_policy_graph import PGTFPolicy
|
|
|
|
# yapf: disable
|
|
# __sphinx_doc_begin__
|
|
DEFAULT_CONFIG = with_common_config({
|
|
# No remote workers by default
|
|
"num_workers": 0,
|
|
# Learning rate
|
|
"lr": 0.0004,
|
|
# Use PyTorch as backend
|
|
"use_pytorch": False,
|
|
})
|
|
# __sphinx_doc_end__
|
|
# yapf: enable
|
|
|
|
|
|
def get_policy_class(config):
|
|
if config["use_pytorch"]:
|
|
from ray.rllib.agents.pg.torch_pg_policy_graph import PGTorchPolicy
|
|
return PGTorchPolicy
|
|
else:
|
|
return PGTFPolicy
|
|
|
|
|
|
PGTrainer = build_trainer(
|
|
name="PG",
|
|
default_config=DEFAULT_CONFIG,
|
|
default_policy=PGTFPolicy,
|
|
get_policy_class=get_policy_class)
|