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.

Sign up for GitHub

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

Jump to bottom

Add experiment 3 #56

Merged
merged 5 commits into from
Aug 16, 2023
Merged

Add experiment 3 #56

merged 5 commits into from
Aug 16, 2023

Conversation

jerry871002
Copy link
Owner

@jerry871002 jerry871002 commented Aug 14, 2023 •
edited
Loading

  • add tau prediction ACC plot with intra-episode markers for BSI-PT and OKR
  • add tau prediction ACC plot for deep-bpr and bpr+

@jerry871002
feat: add tau prediction ACC plot with intra-episode marker
b957eba 
TODO
plot for deep-bpr and bpr+ don't need to show intra-episode
marker, will need another plot function for them
@jerry871002 jerry871002 added the draft The pull request is not ready for review label Aug 14, 2023
@jerry871002 jerry871002 requested a review from YY87927 August 14, 2023 16:07
@jerry871002
feat: add policy prediction ACC for deep-bpr and bpr+ (#52, #53)
25f5376 
since the ACC plot with intra-episode markers is the same in
experiment 2 as in experiment 3, also add the ACC plot in
experiment 2
jerry871002
jerry871002 commented Aug 15, 2023
View reviewed changes
src/baseball_game/env.py Show resolved Hide resolved
src/baseball_game/run.py Outdated Show resolved Hide resolved
@jerry871002
refactor: more robust is_uniform
cae3dd6 
comparing floating point numbers isn't safe, use a small tolerance
number instead
@jerry871002
fix: ensure intra-episode policy prediction is aligned (#51)
d385f39 
the intra-episode policy prediction array wasn't properly aligned
if the agent's belief is an uniform distribution

also separate the logic of the inter- and intra-episode policy
prediction as they are recording different stats
@jerry871002
chore: improve readability of the figures
1412834
@jerry871002 jerry871002 added ready for review The pull request is ready for review and removed draft The pull request is not ready for review labels Aug 16, 2023
@jerry871002 jerry871002 linked an issue Aug 16, 2023 that may be closed by this pull request
Make sure the baseball environment works with run.py #43
Closed
8 tasks
@jerry871002 jerry871002 mentioned this pull request Aug 16, 2023
Closed
8 tasks
@jerry871002 jerry871002 removed a link to an issue Aug 16, 2023
Make sure the baseball environment works with run.py #43
Closed
8 tasks
@jerry871002
Copy link
Owner Author

I will merge this PR without review, let's do the review in #13.

@jerry871002 jerry871002 merged commit 40af7e9 into refactor-exp Aug 16, 2023
@jerry871002 jerry871002 deleted the experiment-3 branch August 16, 2023 13:34
@jerry871002 jerry871002 self-assigned this Aug 16, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@YY87927 YY87927 Awaiting requested review from YY87927

Assignees

@jerry871002 jerry871002

Labels
ready for review The pull request is ready for review
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@jerry871002