Whi Kwon
37e9697b1b
Refactor OpenManipulator env class ( #46 )
...
* Merge subin branch
Squashed commit of the following:
commit 98112b8c05f955b1eb49a6b78023cad0979d5f95
Author: Subin Yang <ysb8049@naver.com >
Date: Sat Mar 30 18:19:46 2019 +0900
Remove noqa
commit f45571a80afd403c8ec56db8a2fb5cbedf288db7
Author: Subin Yang <ysb8049@naver.com >
Date: Sat Mar 30 17:50:39 2019 +0900
Resolve flake8
commit 058d85bc4ed09441d27065e6d304bfb946942a98
Author: Subin Yang <ysb8049@naver.com >
Date: Sat Mar 30 17:41:35 2019 +0900
Modify structures of ros interface and reacher env
commit ae4c859ffa6b008823050f310bdccbee6a1de30a
Author: Subin Yang <ysb8049@naver.com >
Date: Sat Mar 30 17:28:15 2019 +0900
Resolve flake8
commit 4c74ec6527b52d75882ddbe1b4f518f9c252a25c
Author: Subin Yang <ysb8049@naver.com >
Date: Sat Mar 30 17:23:30 2019 +0900
Resolve flake8
commit 243b2f3739b4388d814a886d5cf1b85a05bb526a
Author: Subin Yang <ysb8049@naver.com >
Date: Sat Mar 30 17:18:13 2019 +0900
Add open manipulator environment
* Refactor openmanipulator environment class
* Refactored env structure
* Fix errors
* Fix error
* Add open_manipulator launch file
* Fix errors
* fix error
* fix error
* fix error
* fix error
* fix error
* fix error
* fix error
* Fix typo
* Delete unused script
* Change reward
* Fix typo, add env name to config
* Change demo file compatible to python2 (#40 )
* Change demo file to python2 compatible
* Add object to classes for compatibility with python2
* Refactoring config, envs and ros interface (#48 )
* Refactoring config architecture
* Replace network hyper params on agent config
* Modify env class and ros interface class
* Modify getter and setter on ros interface
* Modify wrong code
* Fix typo
* Add env config
* Final environment class and test scripts before the test (#43 )
* new user branch
* Resolve formatting issues on test scripts
* Resolve formatting issues on test scripts
* Merge subin branch
Squashed commit of the following:
commit 98112b8c05f955b1eb49a6b78023cad0979d5f95
Author: Subin Yang <ysb8049@naver.com >
Date: Sat Mar 30 18:19:46 2019 +0900
Remove noqa
commit f45571a80afd403c8ec56db8a2fb5cbedf288db7
Author: Subin Yang <ysb8049@naver.com >
Date: Sat Mar 30 17:50:39 2019 +0900
Resolve flake8
commit 058d85bc4ed09441d27065e6d304bfb946942a98
Author: Subin Yang <ysb8049@naver.com >
Date: Sat Mar 30 17:41:35 2019 +0900
Modify structures of ros interface and reacher env
commit ae4c859ffa6b008823050f310bdccbee6a1de30a
Author: Subin Yang <ysb8049@naver.com >
Date: Sat Mar 30 17:28:15 2019 +0900
Resolve flake8
commit 4c74ec6527b52d75882ddbe1b4f518f9c252a25c
Author: Subin Yang <ysb8049@naver.com >
Date: Sat Mar 30 17:23:30 2019 +0900
Resolve flake8
commit 243b2f3739b4388d814a886d5cf1b85a05bb526a
Author: Subin Yang <ysb8049@naver.com >
Date: Sat Mar 30 17:18:13 2019 +0900
Add open manipulator environment
* Refactor openmanipulator environment class
* Test the training loop with td3 baseline
* Add one-shot launch file for gazebo initialization
* Refactored env structure
* Fix errors
* Fix error
* Fix errors
* fix error
* fix error
* fix error
* fix error
* fix error
* fix error
* fix error
* Fix typo
* Delete unused script
* Change reward
* Fix typo, add env name to config
* Refactoring config, envs and ros interface (#48 )
* Refactoring config architecture
* Replace network hyper params on agent config
* Modify env class and ros interface class
* Modify getter and setter on ros interface
* Modify wrong code
* Fix typo
* Add env config
* Resolve flake8, typo issue
* Resolve conflict during pull remote
2019-04-09 20:45:21 +09:00
Seungjae Ryan Lee
00c3dc4286
Remove DDPG ( #28 )
...
* Change default algorithm from DDPG to SAC
* Remove DDPG examples
* Remove DDPG algorithms
DDPG, DDPG+PER, DDPGfD
* Fix parser bug in LunarLanderContinuous
2019-03-21 23:51:39 +09:00
Kyunghwan Kim
b4f8bd58b4
Add demo files ( #23 )
...
* Add demo files
* Add demo path on run files and change formatting
* Delete discrete demo
2019-03-14 14:02:24 +09:00
Seungjae Ryan Lee
ca5c99bc41
Add DDPGfD, TD3fD and SACfD ( #22 )
...
* Format repository
* Clone files from medipixel repo
* Fix DDPGfDAgent.update_model()
* Fix bug on _initialize()
* Add demo-path parameter and demo data
* Rename init_priority to _max_priority for PER
This makes PER and PERfD consistent.
* Make i_episode attribute of DDPGAgent
* Clone SAC code from medipixel repo
* Fix update_model() for SACfD
* Fix _initialize() for SACfD
* Add is_discrete attribute to AbstractAgent for SACfD
* Add i_episode attribute to SACAgent for SACfD
* Modularize DDPGAgent and SACAgent
* Modify hyperparameters for DDPGfD and SACfD
* Add NStepBuffer
* Add n-step to DDPGfD
* Add n-step to SACfD
* Add TD3fD without n-step
* Attempt to tune hyperparameters
* Remove discrete environment check in SAC
* Implement n-step on TD3fD
* Fix step function of TD3
No done check, and _add_transition_to_memory was not called.
* Fix actor loss calculation for TD3fD
* Attempt to tune hyperparameters
* Print both critic losses
* Fix typo bug
* Attempt to tune hyperparameters
* Fix bug in n-step demo retrieval
* Fix bug in n-step transition addition
2019-03-14 11:06:54 +09:00
Kyunghwan Kim
ecb42d30d2
Add per ( #8 )
...
* Add per and modify etc
* Replace pre-commit-config.yaml and add pre-commit hook in .git
* Modify .gitignore
* Modify .gitignore
* Modify buffer and code
* Modify replay buffer and per
* Modify .gitignore
2019-02-16 17:30:12 +09:00
Whi Kwon
7f4756a1d4
Add overall setting and ddpg baseline ( #1 )
...
* Add overall CI settings
* Add specific build dir to travis
* Add before install/script condition to travis
* Add ddpg baseline
* Add wandb, remove algorithms except ddpg
* Remove init file in script
* Separate config file for ddpg
* Remove unnecessary examples
* Remove unnecessary args opt
* Add pre-commit setting
* Change pre-commit settings
* Change travis-ci setting
* Fix travis-ci issue
* Modify argparse arguments, fix requirements
* Change arguments order
2019-02-05 20:07:46 +09:00
Whi Kwon