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

test: [RLOS2023] add test for slate #4629

Merged
merged 3 commits into from
Aug 7, 2023

Conversation

michiboo
Copy link
Collaborator

No description provided.

"params": {}
},
"num_slot": 3,
"num_context": 2
Copy link
Member

Choose a reason for hiding this comment

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

We are not using context here, so maybe we can start with 2 separate test scenarios:

  • without context change (with reward function definition similar to what we have now)
  • with context change (and with more explicit context dependency in reward function definition)

reward_function,
logging_policy,
action_space,
num_context=1,
Copy link
Member

Choose a reason for hiding this comment

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

num_context is conflicting with context_name. Can we allow context_name to be a list and infer no_context from it?

return reward[slot - 1][chosen_action - 1]


def reverse_reward_after_iteration(chosen_action, context, slot, **kwargs):
Copy link
Member

Choose a reason for hiding this comment

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

*_after_threshold?

{
"name": "assert_loss",
"params": {
"expected_loss": 0.8,
Copy link
Member

Choose a reason for hiding this comment

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

expected loss should be slightly more than -2, but CI is still green

@ataymano ataymano merged commit 702604f into VowpalWabbit:rlos2023/test Aug 7, 2023
ataymano added a commit that referenced this pull request Oct 5, 2023
* intro notebook

* test: [RLOS_2023][WIP] updated test for regression weight  (#4600)

* test: add test for regression weight

* test: make test more reusable by using json to specify pytest

* test: minor fix on naming

* test: add and option to python json test

* test: [RLOS_2023]  test for contextual bandit (#4612)

* test: add basic cb test and configuration

* test: add shared context data generation

* add test for cb_explore_adf

* test: dynamically create pytest test case

* test: give fixed reward function signature

* test: [RLOS_2023] [WIP] Support + and * expression for grids (#4618)

* test: add basic cb test and configuration

* test: add shared context data generation

* add test for cb_explore_adf

* test: dynamically create pytest test case

* test: give fixed reward function signature

* test: support + and * expression for grids

* fix empty expression bugs

* test: [RLOS2023] [WIP] add more arguments for reg&cb tests (#4619)

* test: add more arguments for reg&cb tests

* test: fix minor bug in generate expression & add loss funcs to tests

* test: [RLOS2023] [WIP] add classification test (#4623)

* test: add more arguments for reg&cb tests

* test: fix minor bug in generate expression & add loss funcs to tests

* test: add test for classification

* test: organize test framework structure (#4624)

* test: [RLOS2023][WIP] add option for storing output and grid language redefinition (#4627)

* test: redesign grid lang

* test: add option for store output

* test: change list to dict for config vars

* test: [RLOS2023] add test for slate (#4629)

* test: add test for slate

* test: test cleanup and slate test update

* test: minor cleanup and change assert_loss function to equal instead of lower

* test: [RLOS2023] add test for cb with continous action  (#4630)

* test: add test for slate

* test: test cleanup and slate test update

* test: minor cleanup and change assert_loss function to equal instead of lower

* test: add test for cb with continous action

* modify blocker testcase

* test: [RLOS2023] clean for e2e testing framework v2 (#4633)

* test: clean for e2e test v2

* test:change seed to same value for all tests

* test: add datagen driver (#4638)

* python black

* python black 2

* minor demo cleanup

---------

Co-authored-by: Alexey Taymanov <[email protected]>
Co-authored-by: Alexey Taymanov <[email protected]>
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