Whi Kwon
4c300129d6
Merge branch 'master' into feat/demo_refactoring
2019-08-17 14:21:55 +09:00
Geonhee
055d97661e
Implement cam in GAZEBO ( #90 )
...
* Create urdf file
* add the urdf file for implementing camera
* create launch file for executing gazebo including cam
* remove the dummy
* remove dummy
* change directory
2019-08-10 16:55:18 +09:00
Whi Kwon
1b733a9f4c
Fix episode never ending issue ( #88 )
2019-07-25 22:57:08 +09:00
Kyunghwan Kim
ede6fa3c7a
Add HER on sac ( #85 )
...
* Add HER on sac
* Add args in wandb log
2019-07-20 17:36:01 +09:00
Whi Kwon
2127ec5330
Merge branch 'master' into feat/demo_refactoring
2019-07-19 23:13:53 +09:00
Whi Kwon
4856da56c0
Remove duplicate code ( #86 )
2019-07-19 23:13:19 +09:00
Whi Kwon
61471fdf9c
Fix dockerfile ( #84 )
...
* Fix dockerfile
* Fix wrong filename
2019-07-19 00:11:29 +09:00
Whi Kwon
eca154897e
Merge branch 'master' into feat/demo_refactoring
2019-07-12 01:27:11 +09:00
Whi Kwon
0fac485205
Modified demo config and run demo script ( #83 )
...
* Add removed q_dot scaling factor
* Refactored cubic function
* Separate config and add run file.
* Resolve flake8 issue
* Resolve flake8 issue
* Remove whitespace before ( issue
2019-07-12 01:26:34 +09:00
Subin Yang
2f8dbf5249
Modify docstrings and resolve flake8 ( #82 )
2019-07-11 23:02:04 +09:00
ohwi
b03336c689
Change key for ROS download ( #80 )
2019-07-10 19:06:03 +09:00
Whi Kwon
02ba6e947d
Refactored demo_collector ( #79 )
...
* Refactored the code
* Add removed q_dot scaling factor
* Refactored cubic function
* Fix Python2 floating issue
* Resolve flake8 issue
2019-07-10 00:23:10 +09:00
Whi Kwon
9622c83cea
Remove if/else conditional statements in run ( #74 )
2019-07-06 16:26:30 +09:00
Subin Yang
48fc2f56d5
Add docstring ( #75 )
2019-07-06 00:20:37 +09:00
Whi Kwon
2e05c7fe48
Gather demo collection at once ( #72 )
2019-07-05 18:40:47 +09:00
Subin Yang
3e224f1bed
Proceed refactoring of demo collector
...
Proceed refactoring of demo collector. Add docstrings. Fix ros
param key error bug.
2019-07-04 09:06:22 +09:00
Whi Kwon
7fff8e3d5a
Merge branch 'master' into feat/demo_refactoring
2019-06-26 23:35:01 +09:00
Whi Kwon
9c2475498c
Modify terminal done state ( #65 )
2019-06-26 23:33:38 +09:00
whikwon
d279d52d9f
Remove comment to install pre-commit:
2019-06-03 22:04:00 +09:00
Whi Kwon
9264c03f76
Add installation guide for openmanipulator local training ( #63 )
2019-05-31 15:23:58 +09:00
kdh0429
8cbfe50a9e
Add doctrings and change file directory
2019-05-30 23:25:09 +09:00
Whi Kwon
09b1f2e9a8
Fix episode unreset bug ( #62 )
2019-05-30 22:39:44 +09:00
Whi Kwon
47593785ad
Fix success_count not reset issue ( #59 )
2019-05-30 22:01:43 +09:00
kdh0429
bd1711305b
Proceed refactoring of demo collector
2019-05-28 14:34:17 +09:00
Cheolhui
af95ab14f6
Replace the fk solver with kdl kinematics ( #53 )
...
* Replace the fk solver with kdl kinematics
* Resolve the wrong kdl kinematics due to ill robot tree structure
* Apply isort and black and apply some naming changes
* Remove white spaces, blanks
* Change file permission 755 to 644
* Change file permission 755 to 644
* Change file permission 755 to 644
* Change file permission 755 to 644
* Change file permission 644 to 755
2019-05-25 00:15:25 +09:00
Whi Kwon
4b56ae781b
Modify docker related commands ( #54 )
...
* Add new ros package installation(orocos, hrl-kdl)
* Add source bashrc
* update train script
* Add custom package ros
* Change delegating env_name logic
* Add reacher env when training selection
* Change clone branch to master
2019-05-21 13:26:52 +09:00
Whi Kwon
5ff59a280e
Add installation, train documentation ( #55 )
...
* Add docker/local train guidelines
* Add wandb log info
* Add environment
* Remove duplicated commands
* Add environment info
* Add period
2019-05-21 12:00:29 +09:00
Whi Kwon
c1f348775e
Add openmanipulator simulation environment agent ( #50 )
2019-05-03 21:25:15 +09:00
Whi Kwon
16ae4375c9
Change demo file compatible to python2 ( #40 )
...
* Change demo file to python2 compatible
* Add object to classes for compatibility with python2
2019-04-07 13:06:39 +09:00
Whi Kwon
a130293f8b
Add dockerfile, docker training script ( #38 )
...
* Add td3, td3fd reacher training scripts
* Add sacfd reacher.v2 training script
* Change sac hyperparameter to be equal to sacfd
* Adjust black formatting
* Modify dockerfile
* Changed install branch master to kinetic-devel
* Added dockerignore
* Update docker related files
* Modify shell script
* Add pip installation
* Fix pip issue
* tmp commit
* Modify docker related files
* Remove unused conditions
* Remove python3 scripts
* Remove unused files
* Recover sac parameter
2019-03-30 14:58:01 +09:00
Kyunghwan Kim
35f5524cd7
Replace installing python3.6 command on Makefile ( #41 )
...
* Modify Makefile
* Modify .travis.yml
* Replace make command on .travis.yml
2019-03-30 14:48:45 +09:00
Whi Kwon
596bd7f289
Organize ROS related files ( #37 )
...
* Modify ROS related files
* Remove unused packages
2019-03-25 21:32:03 +09:00
Kyunghwan Kim
d2769dfa9d
Convert code to python 2.7 ( #35 )
...
* Convert code format to python2.7 (SAC)
* Convert code format python2.7 (TD3, all fD)
* Remove no use import and black setting
* Change SAC param
* Change env name Reacher-v2 to v1
* Remove old version reacher training script
* Convert code format python2.7
* Modify .travis.yml
* Add install command python3.6 & black on Makefile
* Fix seperator to tab on Makefile
* Modify Makefile
* Fix little error
* Change td3 gamma parameter
2019-03-25 19:07:19 +09:00
Seungjae Ryan Lee
81a9d861b6
Improve README design and content ( #30 )
...
* Add logo to README
* Add status shields to README
* Align status shields to center
* Add elevator pitch line to README
* Add Algorithms section to README
* Add How to Cite section
* Remove Repository Structure section
* Add basic Installation section
2019-03-25 18:53:36 +09:00
Whi Kwon
759caebf2b
Add Reacher-v2 training scripts (SAC, SACfD, TD3, TD3fD) ( #36 )
...
* Add td3, td3fd reacher training scripts
* Add sacfd reacher.v2 training script
* Change sac hyperparameter to be equal to sacfd
* Adjust black formatting
* Remove ddpg reacher example
2019-03-24 13:48:47 +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
Whi Kwon
ee014e5a93
Add first dockerfile ( #16 )
2019-03-12 20:51:22 +09:00
Whi Kwon
d7b09d1bd5
Add LSTM network ( #15 )
...
* Add common lstm module
* Add wave_test notebook
* Add lstm test example (sin -> cos)
* Add LSTM test case(sine+noise->cos)
* Move test_lstm file
* Add legend to distinguish label
* Fix flake8
* Add matplotlib to requirements
2019-03-05 09:25:38 +09:00
Whi Kwon
5962ff5277
Add TD3 ( #10 )
...
* Add td3
* Fix flake8
* Fix action clamping
* Increase episode max step, add detach to actor_loss
* Fix actor update freq bug
* 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
* Add random initial action in ddpg (#13 )
* Add random initial actions in ddpg
* Add reacher-v2 example of ddpg
* Add soft actor critic (#12 )
* Add soft actor critic
* Delete unnecessary examples
* Add td3
* Fix flake8
* Fix action clamping
* Fix flake8
* Increase episode max step, add detach to actor_loss
* Fix actor update freq bug
* Fix code to reflect PR
* Resolve conflict
2019-02-24 13:44:20 +09:00
Jinwoo Park (Curt)
4a19053d25
Add soft actor critic ( #12 )
...
* Add soft actor critic
* Delete unnecessary examples
2019-02-18 17:54:07 +09:00
Jinwoo Park (Curt)
d2b670015c
Add random initial action in ddpg ( #13 )
...
* Add random initial actions in ddpg
* Add reacher-v2 example of ddpg
2019-02-18 08:57:36 +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
Seungjae Ryan Lee
c7362ee828
Add overall structure to package
2019-02-03 17:16:55 +09:00