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

Integrate Optuna into XuanCe as the primary tool for hyperparameter optimization, demonstrated with a DQN example #75

Closed
wenzhangliu opened this issue Jan 9, 2025 · 0 comments
Closed

Integrate Optuna into XuanCe as the primary tool for hyperparameter optimization, demonstrated with a DQN example #75

wenzhangliu opened this issue Jan 9, 2025 · 0 comments
Milestone
Support auto hype...

Comments

@wenzhangliu
Copy link
Collaborator

To enhance the hyperparameter optimization capabilities of XuanCe, we propose integrating Optuna as the primary tool for tuning hyperparameters. This integration aims to simplify configuration processes for users and provide insightful guidance, ensuring more efficient and effective training of reinforcement learning models. The integration will be exemplified using the Deep Q-Network (DQN) algorithm to demonstrate Optuna’s capabilities within the XuanCe framework.

Optuna Documentation: https://optuna.org/.
wenzhangliu added a commit that referenced this issue Jan 9, 2025
@wenzhangliu
support optuna for dqn (#75)
df70d8d
wenzhangliu added a commit that referenced this issue Jan 10, 2025
@wenzhangliu
docs for hyperpameters tuning (#75)
b55f758
wenzhangliu added a commit that referenced this issue Jan 10, 2025
@wenzhangliu
docs for hyperpameters tuning (#75)
ff62dbf
xiaoyangquan2002 pushed a commit to xiaoyangquan2002/xuance that referenced this issue Jan 11, 2025
@wenzhangliu
docs for hyperpameters tuning (agi-brain#75)
d3b923b
xiaoyangquan2002 pushed a commit to xiaoyangquan2002/xuance that referenced this issue Jan 11, 2025
@wenzhangliu
docs for hyperpameters tuning (agi-brain#75)
5fb4fa9
wenzhangliu added a commit that referenced this issue Jan 11, 2025
@xiaoyangquan2002 @wenzhangliu
update DQN document (#82)
fd03c88 
* td3算法简介

* docs for hyperpameters tuning (#75)

* docs for hyperpameters tuning (#75)

* api documentation for tuning tools

* api documentation for tuning tools

* api documentation for tuning tools

* api documentation for tuning tools

* update DQN document

---------

Co-authored-by: xiaoyangquan2002 <[email protected]>
Co-authored-by: wenzhangliu <[email protected]>
wenzhangliu added a commit that referenced this issue Feb 8, 2025
@wenzhangliu @TangY1fan
@xiaoyangquan2002 @XiangDuojie
v1.2.6 (#104)
36b378d 
* extensive examples

* update coma and add examples

* examples for marl

* update the installation of SMAC

* arguments list

* update docs

* update discord invite link

* update dqn docs

* support optuna for dqn (#75)

* hyperparams for ddqn

* contributing to us

* agent.current_step (#79)

* pdqn_agent.md commit (#80)

* pdqn_agent.md commit1

* pdqn_agent.md commit2

* update readme and move demo to examples

* td3算法简介 (#81)

Co-authored-by: xiaoyangquan2002 <[email protected]>

* docs for hyperpameters tuning (#75)

* docs for hyperpameters tuning (#75)

* api documentation for tuning tools

* api documentation for tuning tools

* api documentation for tuning tools

* api documentation for tuning tools

* update DQN document (#82)

* td3算法简介

* docs for hyperpameters tuning (#75)

* docs for hyperpameters tuning (#75)

* api documentation for tuning tools

* api documentation for tuning tools

* api documentation for tuning tools

* api documentation for tuning tools

* update DQN document

---------

Co-authored-by: xiaoyangquan2002 <[email protected]>
Co-authored-by: wenzhangliu <[email protected]>

* hyperparameters setting for other algorithms (#77)

* hyperparameters setting for marl algorithms (#77)

* hyperparameters setting for marl algorithms (#77)

* update test files

* add basic examples for drl

* test for hyperparameters tuning

* update qrdqn configs

* a2c_agent.md commit (#90)

* pdqn_agent.md commit1

* pdqn_agent.md commit2

* a2c_agent.md commit-1

* add SAC document (#92)

* add SAC document

* update TD3 document

* update sac document

* update TD3 document

---------

Co-authored-by: xiaoyangquan2002 <[email protected]>

* DDPG.md (#93)

* add SAC document (#94)

* add SAC document

* update TD3 document

* update sac document

* update TD3 document

---------

Co-authored-by: xiaoyangquan2002 <[email protected]>

* example for dqn tuning

* hyperparameters tuning

* update configs

* remove to examples

* Add README_CN.md

* update readme

* update readme

* tune example

* installation for torch-scatter (#73)

* update

* multi-objective tuning

* return information during training #96

* itemgetter for one agent #97

* selected objectives for multi-objective tuning #98

* selected objectives for multi-objective tuning #98

* update readme

* installation

* environment link

* environment link

* docs for multi-objective tuning #100

* Add NPG agent and NPG learner (#102)

* complete the installation docs for torch-scatter #73

* complete the docs for multi-objective tuning #100

* environments

* environments

* complete the docs for multi-objective tuning #100

* npg config files #84

* usage update

* Add npg_agent.md (#103)

* Add NPG agent and NPG learner

* Add npg_agent.md and npg_learner.rst

* docs for npg

* npg index

* npg comments

* npg docs

* distributed training docs

* distributed training docs

* api annotation for operations

* update readme

* set_device

* v1.2.6

---------

Co-authored-by: TangY1fan <[email protected]>
Co-authored-by: xiaoyangquan2002 <[email protected]>
Co-authored-by: xiaoyangquan2002 <[email protected]>
Co-authored-by: XiangDuojie <[email protected]>
@wenzhangliu wenzhangliu mentioned this issue Feb 8, 2025
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
Support auto hyperparameters optimiza...
Development

No branches or pull requests
1 participant
@wenzhangliu