Using dist.mode instead of logits.argmax. More compact. #1066
Conversation
|
@arnaujc91 a test fails due to cryptic float/rounding errors. Could you introduce a rounding to say 5 digits to make sure the test succeeds? |
Please check test modifications. |
Codecov ReportAll modified and coverable lines are covered by tests ✅
❗ Your organization needs to install the Codecov GitHub app to enable full functionality. Additional details and impacted files@@ Coverage Diff @@
## master #1066 +/- ##
==========================================
+ Coverage 88.16% 88.17% +0.01%
==========================================
Files 100 100
Lines 8176 8172 -4
==========================================
- Hits 7208 7206 -2
+ Misses 968 966 -2
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. |
|
@arnaujc91 pls resolve the conflicts with master |
done |
changed all the occurrences where an action is selected deterministically - **from**: using the outputs of the actor network. - **to**: using the mode of the PyTorch distribution. --------- Co-authored-by: Arnau Jimenez <[email protected]>
changed all the occurrences where an action is selected deterministically - **from**: using the outputs of the actor network. - **to**: using the mode of the PyTorch distribution. --------- Co-authored-by: Arnau Jimenez <[email protected]>
changed all the occurrences where an action is selected deterministically - **from**: using the outputs of the actor network. - **to**: using the mode of the PyTorch distribution. --------- Co-authored-by: Arnau Jimenez <[email protected]>
changed all the occurrences where an action is selected deterministically - **from**: using the outputs of the actor network. - **to**: using the mode of the PyTorch distribution. --------- Co-authored-by: Arnau Jimenez <[email protected]>
changed all the occurrences where picking an action deterministically
This was agreed with @MischaPanch.
Please make sure everything is alright.