Skip to content
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.

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

cart_pole #7

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

cart_pole #7

wants to merge 1 commit into from

Conversation

wsredniawa
Copy link
Contributor

No description provided.

# print(observation)
obs,reward,done,info=env.step(action)
# print(obs)
obs = np.array([1,1,1,1])*100
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

obs from env is updated by a constant array, why?

for t in range(100):
env_vis.append(env.render(mode='rgb_array'))
# print(observation)
obs,reward,done,info=env.step(action)
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You update your own reward by env reward in each step, and only env reward goes to the agent.step() function

obs,reward,done,info=env.step(action)
# print(obs)
obs = np.array([1,1,1,1])*100
output_spikes_ms=agent.step(observation=abs(obs.reshape((2,2))), reward=reward)
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

with the new version of Agent - I think we should use:

  • agent.reward_step() for reward only
  • agent.step() for step only

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants