Skip to content

Make RL training compatible with PyTorch #1520

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.

Sign up for GitHub

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

Merged
merged 4 commits into from
Oct 9, 2020
Merged

Make RL training compatible with PyTorch #1520

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f9319c2
Make RLEstimator() PyTorch compatible & modify cartpole notebook
annaluo676 Sep 16, 2020
2b7c6df
set use_pytorch to False by default
annaluo676 Sep 16, 2020
eb62e54
minor refactor; check in first unit test
annaluo676 Oct 7, 2020
b7c09cd
indent correction
annaluo676 Oct 7, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
indent correction
  • Loading branch information
@annaluo676
annaluo676 committed Oct 7, 2020
commit b7c09cd3fa3573511390e33e56ab7d6f982e96ee
16 changes: 8 additions & 8 deletions reinforcement_learning/common/sagemaker_rl/ray_launcher.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -234,14 +234,14 @@ def create_tf_serving_model(self, algorithm=None, env_string=None):
cls = get_agent_class(algorithm)
with open(os.path.join(MODEL_OUTPUT_DIR, "params.json")) as config_json:
config = json.load(config_json)
print("Loaded config for TensorFlow serving.")
config["monitor"] = False
config["num_workers"] = 1
config["num_gpus"] = 0
agent = cls(env=env_string, config=config)
checkpoint = os.path.join(MODEL_OUTPUT_DIR, "checkpoint")
agent.restore(checkpoint)
export_tf_serving(agent, MODEL_OUTPUT_DIR)
print("Loaded config for TensorFlow serving.")
config["monitor"] = False
config["num_workers"] = 1
config["num_gpus"] = 0
agent = cls(env=env_string, config=config)
checkpoint = os.path.join(MODEL_OUTPUT_DIR, "checkpoint")
agent.restore(checkpoint)
export_tf_serving(agent, MODEL_OUTPUT_DIR)

def save_checkpoint_and_serving_model(self, algorithm=None, env_string=None, use_pytorch=False):
self.save_experiment_config()
Expand Down