feature(wrh): add continuous action space in mt for unizero. #271
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
Contributor
ruiheng123
commented
Aug 26, 2024
ruiheng123
commented
- Continuous action space in unizero-mt added (to be tested)
* feature(pu): add lightzero sphinx docs * feature(pu): add .readthedocs.yaml * polish(pu): move .readthedocs.yaml to the root directory * polish(pu): polish sphinx requirements * polish(pu): polish recommonmark requirements * fix(pu): fix api_doc and use sphinx_rtd_theme * fix(pu): fix .readthedocs.yaml * fix(pu): fix .readthedocs.yaml * fix(pu): fix .readthedocs.yaml * fix(pu): fix conf.py * fix(pu): fix requirements-doc.txt * fix(pu): fix requirements-doc.txt * fix(pu): fix requirements-doc.txt * fix(pu): fix requirements-doc.txt * polish(pu): delete doc/zh_CN * polish(pu): polish conf.py * polish(pu): polish conf.py * polish(pu): polish deploy.yml for docs * fix(pu): Update GitHub Actions workflow and add .nojekyll file * polish(pu): polish deploy.yml for docs * polish(pu): polish deploy.yml for docs * polish(pu): polish deploy.yml for docs * polish(pu): polish deploy.yml for docs * polish(pu): polish deploy.yml for docs * polish(pu): polish deploy.yml for docs * polish(pu): polish documentation
* Add Harmony Dream * feature(wrh): add harmony dream * feature(wrh) add harmony dream to muzero * feature(wrh) add harmony dream to muzero * feature(wrh) add harmony dream to muzero * feature(wrh): add harmony dream
* feature(xcy): add meta drive env * polish(xcy):change config * feature(xcy):change metadrive version * polish(xcy):polish the config and comments --------- Co-authored-by: 蒲源 <[email protected]>
* feature(hus): add self-hosted runner * revert commit c004eac opendilab@c004eac
…pendilab#260) * feature(pu): add dmc2gym and related configs * fix(pu): fix sampled_efficientzero_model for dmc2gym * sync code * polish(pu): polish sez config for dmc2gym and lunarlander * feature(pu): add Sampled MuZero * feature(pu): add lunarlander sampled muzero config * feature(pu): add sampled unizero and its pendulum config * feature(pu): add sampled unizero's lunarlander and bipedalwalker config * sync code * polish(pu): polish sampled muzero * fix(pu): fix min_max_stats bug in ctree_sampled_muzero * fix(pu): fix min_max_stats bug in ctree_sampled_muzero * polish(pu): polish sampled related configs * feature(pu): add dmc2gym sampled related configs * fix(pu): fix dmc2gym suz config * fix(pu): use LN in sampled unizero * polish(pu): use sim_norm in act_embedding in continuous action space * fix(pu): fix expand bug in policy_loss of sampled unizero * polish(pu): polish sampled unziero lunarlander configs * fix(pu): fix sampled unizero action .long() bug in continuous action space * polish(pu): polish dmc state sampled-unizero configs * fix(pu): fix label_policy in sampled unizero * polish(pu): polish sampled related env/configs/policy/model/buffer * polish(pu): update readme --------- Co-authored-by: dyyoungg <[email protected]> Co-authored-by: jiayilee65 <[email protected]>
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.