fhswf / MLPro

MLPro - The Integrative Middleware Framework for Standardized Machine Learning in Python
https://mlpro.readthedocs.io/
Apache License 2.0
12 stars 3 forks source link

Bug: Reward.C_TYPE_EVERY_AGENT always logging NaN #861

Closed steveyuwono closed 1 year ago

steveyuwono commented 1 year ago

1 Describe the bug When we set an RL environment and GT game board with Reward.C_TYPE_EVERY_AGENT, our data storing functionality always stores NaN instead of the correct values of the reward. There is a difference between 'self._ds_rewards.get_space().get_dim_ids()' and 'self._ds_rewards.agents_id', therefore the correct values of the reward could not be called.

2 To Reproduce Steps to reproduce the behavior:

  1. Go to '...'
  2. Click on '....'
  3. Scroll down to '....'
  4. See error

3 Expected behavior A clear and concise description of what you expected to happen.

4 Screenshots If applicable, add screenshots to help explain your problem.

5 Additional Informations

5.1 Operating System