feature(zc): add bcq algorithm #640
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
add paper link and a training curve figure in PR |
zjowowen
reviewed
Apr 12, 2023
ding/example/bcq.py
Outdated
| from ding.utils import set_pkg_seed | ||
| from dizoo.d4rl.envs import D4RLEnv | ||
| from dizoo.d4rl.config.halfcheetah_medium_bcq_config import main_config, create_config | ||
| # from dizoo.d4rl.config.halfcheetah_medium_expert_edac_config import main_config,create_config |
zjowowen
reviewed
Apr 12, 2023
| vae_hidden_dims: List = [750, 750], | ||
| phi: float = 0.05 | ||
| ) -> None: | ||
| super(BCQ, self).__init__() |
zjowowen
reviewed
Apr 12, 2023
ding/model/template/bcq.py
Outdated
| different computation graph, including ``compute_actor`` and ``compute_critic`` in QAC. | ||
| Mode compute_actor: | ||
| Arguments: | ||
| - inputs (:obj:`torch.Tensor`): Observation data, defaults to tensor. |
There was a problem hiding this comment.
arguments object type is Union[torch.Tensor, Dict[str, torch.Tensor]] for inputs?
zjowowen
reviewed
Apr 12, 2023
dizoo/d4rl/entry/d4rl_bcq_main.py
Outdated
|
|
||
| def train(args): | ||
| # launch from anywhere | ||
| config = Path(__file__).absolute().parent.parent / 'config' / args.config |
There was a problem hiding this comment.
import from dizoo config file directly?
There was a problem hiding this comment.
yes, I copy this from other d4rl_*_main.py
Codecov Report
@@ Coverage Diff @@
## main #640 +/- ##
==========================================
+ Coverage 82.34% 82.49% +0.15%
==========================================
Files 584 583 -1
Lines 47270 47698 +428
==========================================
+ Hits 38924 39350 +426
- Misses 8346 8348 +2
Flags with carried forward coverage won't be shown. Click here to find out more.
|
PaParaZz1
approved these changes
May 30, 2023
PaParaZz1
approved these changes
May 30, 2023
PaParaZz1
approved these changes
May 30, 2023
PaParaZz1
approved these changes
May 30, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Add bcq algorithm
TODO
Add algorithm and config
BCQ paper :https://arxiv.org/pdf/1812.02900.pdf
reference implementation :https://github.com/sfujim/BCQ
Check List