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

A2C algorithm doesnt work #37

Open
Acejoy opened this issue Feb 27, 2024 · 0 comments
Open

A2C algorithm doesnt work #37

Acejoy opened this issue Feb 27, 2024 · 0 comments

Comments

@Acejoy
Copy link

Acejoy commented Feb 27, 2024

Hey ,
I tried chapter-11 notebook and ran the A2C algorithm for training. The agent doesnt learn anything.
I am pasting the logs below:

el 00:00:36, ep 1427, ts 013537, ar 10 001.0±000.0, 100 001.0±000.0, ex 100 0.0±0.0, ev 009.5±000.7
el 00:01:06, ep 3335, ts 031432, ar 10 001.0±000.0, 100 001.0±000.0, ex 100 0.0±0.0, ev 009.5±000.6
el 00:01:37, ep 5295, ts 049762, ar 10 001.0±000.0, 100 001.0±000.0, ex 100 0.0±0.0, ev 009.3±000.8
el 00:02:07, ep 7101, ts 066745, ar 10 001.0±000.0, 100 001.0±000.0, ex 100 0.0±0.0, ev 009.5±000.7
el 00:02:37, ep 8996, ts 084474, ar 10 001.0±000.0, 100 001.0±000.0, ex 100 0.0±0.0, ev 009.2±000.8
el 00:03:07, ep 10812, ts 101495, ar 10 001.0±000.0, 100 001.0±000.0, ex 100 0.0±0.0, ev 009.3±000.7
el 00:03:37, ep 12534, ts 117600, ar 10 001.0±000.0, 100 001.0±000.0, ex 100 0.0±0.0, ev 009.4±000.9
el 00:04:07, ep 14259, ts 133695, ar 10 001.0±000.0, 100 001.0±000.0, ex 100 0.0±0.0, ev 009.4±000.8
el 00:04:37, ep 15967, ts 149650, ar 10 001.0±000.0, 100 001.0±000.0, ex 100 0.0±0.0, ev 009.4±000.7
el 00:05:07, ep 17651, ts 165403, ar 10 001.0±000.0, 100 001.0±000.0, ex 100 0.0±0.0, ev 009.4±000.7
el 00:05:37, ep 19366, ts 181470, ar 10 001.0±000.0, 100 001.0±000.0, ex 100 0.0±0.0, ev 009.4±000.8
el 00:06:07, ep 21014, ts 197042, ar 10 001.0±000.0, 100 001.0±000.0, ex 100 0.0±0.0, ev 009.3±000.8
el 00:06:37, ep 22672, ts 212565, ar 10 001.0±000.0, 100 001.0±000.0, ex 100 0.0±0.0, ev 009.5±000.8
el 00:07:07, ep 24350, ts 228283, ar 10 001.0±000.0, 100 001.0±000.0, ex 100 0.0±0.0, ev 009.5±000.8
el 00:07:37, ep 25916, ts 242947, ar 10 001.0±000.0, 100 001.0±000.0, ex 100 0.0±0.0, ev 009.3±000.8

....

I tried experimenting with entropy_weight but the result remains the same.

Can anyone point out the mistake?
Thanks

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

No branches or pull requests

1 participant