aws / aws/amazon-sagemaker-examples
'main_level/agent/main/online/network_1/ppo_head_0/policy' refers to an Operation not in the graph.
- Dominant language
- Jupyter Notebook
- Stars
- 11k
- Forks
- 7k
- Avg merge
- 8h 29m
- Merged PRs (30d)
- 8
Description
When running the amazon-sagemaker-examples/reinforcement_learning/rl_stock_trading_coach_customEnv/ does not save model and gives the following error:
KeyError: "The name 'main_level/agent/main/online/network_1/ppo_head_0/policy' refers to an Operation not in the graph."
This example uses dueling_q and not ppo. I believe something the _tf_save_model in coach_launcher.py has to be appropiately changed.
Contributor guide
Research direction
Reproduce the failure in reinforcement_learning/rl_stock_trading_coach_customEnv/, then inspect coach_launcher.py and its _tf_save_model entry point. Trace how the dueling_q model is saved and verify the completed change saves the model without looking up the PPO operation that is absent from the graph.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- aws, jupyter-notebook, python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100