ottofabian
|
80933eba09
|
unified API wrapper and updated examples
|
2021-07-02 13:09:56 +02:00 |
|
Marcel
|
87eb093c2c
|
Add open ai gym environments
|
2021-07-01 14:55:14 +02:00 |
|
ottofabian
|
6607d9cff9
|
fixed imports
|
2021-06-30 15:47:06 +02:00 |
|
ottofabian
|
eae149f838
|
added rendering to DMC envs and updated examples
|
2021-06-30 15:00:36 +02:00 |
|
ottofabian
|
7c04b25eec
|
finalized examples and added seed control
|
2021-06-29 16:17:18 +02:00 |
|
ottofabian
|
3b215cd877
|
added dmc2gym conversion and example how to leverage DMPs
|
2021-06-28 17:25:53 +02:00 |
|
ottofabian
|
c8742e2934
|
updated envs and registering
|
2021-06-25 16:17:22 +02:00 |
|
ottofabian
|
0a1e55d97b
|
improved docs and modularity of env helpers
|
2021-06-25 16:17:22 +02:00 |
|
ottofabian
|
29b8c3a6c7
|
renaming
|
2021-06-25 16:17:22 +02:00 |
|
ottofabian
|
3c774382b7
|
Fixed passing arguments to new wrapper structure
|
2021-06-25 16:17:22 +02:00 |
|
ottofabian
|
c0e036b2e5
|
Updated Ball in a cup example for new wrappers
|
2021-06-25 16:17:22 +02:00 |
|
ottofabian
|
dffa3e3682
|
matched file structure of classic control with other tasks
|
2021-06-25 16:17:22 +02:00 |
|
ottofabian
|
a30bdb8ce5
|
updated simple reacher example to new structure
|
2021-06-25 16:17:22 +02:00 |
|
ottofabian
|
e1dc3eeddf
|
updated simple reacher example to new structure
|
2021-06-25 16:17:22 +02:00 |
|
ottofabian
|
f3d837349a
|
updated via point reacher example to new structure
|
2021-06-25 16:17:22 +02:00 |
|
ottofabian
|
fa7dfdc081
|
updated hole reacher example to new structure
|
2021-06-25 16:17:22 +02:00 |
|
ottofabian
|
c5109ec2e7
|
updated hole reacher example to new structure
|
2021-06-25 16:17:22 +02:00 |
|
Maximilian Huettenrauch
|
e7525f61aa
|
wip
|
2021-06-24 18:34:39 +02:00 |
|
ottofabian
|
ed75d565e2
|
fixed hole width for HoleReacher-v1
|
2021-06-24 11:39:59 +02:00 |
|
ottofabian
|
4c334b1129
|
Hole Reacher extended to have holes in both directions
|
2021-06-24 11:39:26 +02:00 |
|
ottofabian
|
6b0dfd7c24
|
Added proper action clipping to MP
|
2021-06-24 11:38:30 +02:00 |
|
Maximilian Huettenrauch
|
c4a698b1bc
|
use mp api
|
2021-06-23 18:23:37 +02:00 |
|
Maximilian Huettenrauch
|
af8e868309
|
merge api support
|
2021-06-22 14:24:28 +02:00 |
|
Maximilian Huettenrauch
|
9b9b092349
|
start refactor and biac dev merge
|
2021-06-22 14:19:42 +02:00 |
|
Maximilian Huettenrauch
|
8075655301
|
update
|
2021-06-22 10:27:25 +02:00 |
|
Marcel
|
4279414656
|
Add interface for envs controlable by a PD Controller and add more infos to mp_wrapper info return value
|
2021-06-21 16:27:48 +02:00 |
|
Maximilian Huettenrauch
|
3876478b96
|
updates
|
2021-06-16 10:29:38 +02:00 |
|
Maximilian Huettenrauch
|
a0a9c9c7fb
|
wip
|
2021-06-01 16:52:54 +02:00 |
|
Maximilian Huettenrauch
|
4aa31a004a
|
updates and bugfix in detpmp_wrapper
|
2021-05-27 17:09:11 +02:00 |
|
Maximilian Huettenrauch
|
f5f12c846f
|
updates on mp wrappers and some bugfixes
|
2021-05-27 17:09:11 +02:00 |
|
ottofabian
|
17c489d622
|
fixed incorrect sampling in hole reacher
|
2021-05-19 18:02:34 +02:00 |
|
ottofabian
|
724b8c6c61
|
fixed hole reacher bug
|
2021-05-18 15:27:08 +02:00 |
|
ottofabian
|
e331803230
|
changed import
|
2021-05-18 10:53:30 +02:00 |
|
ottofabian
|
6169ede449
|
removed episodic_simple_reacher.py
|
2021-05-18 10:50:30 +02:00 |
|
ottofabian
|
e7dcdf38f1
|
removed hole_reacher_v2.py
|
2021-05-18 10:49:08 +02:00 |
|
ottofabian
|
7695cae076
|
default observation selection for MPs
|
2021-05-18 10:39:30 +02:00 |
|
ottofabian
|
528b7521b6
|
removed legacy wrappers
|
2021-05-17 17:59:28 +02:00 |
|
ottofabian
|
14c60766c2
|
fixed open issues
|
2021-05-17 17:58:33 +02:00 |
|
Maximilian Huettenrauch
|
b39104a449
|
merge
|
2021-05-17 12:49:15 +02:00 |
|
Maximilian Huettenrauch
|
7f512068c9
|
context wip
|
2021-05-17 09:32:51 +02:00 |
|
ottofabian
|
6ae195962c
|
adjusted classic control environments to new interface
|
2021-05-12 17:48:57 +02:00 |
|
ottofabian
|
95e9b8be47
|
added MPEnv
|
2021-05-12 09:52:25 +02:00 |
|
Maximilian Huettenrauch
|
b4ad3e6ddd
|
wip
|
2021-05-10 12:17:52 +02:00 |
|
Maximilian Huettenrauch
|
36bf9b5b6a
|
start contextual dmp wrapper
|
2021-05-07 09:51:53 +02:00 |
|
Maximilian Huettenrauch
|
c307383873
|
fix rendering
|
2021-04-30 16:22:33 +02:00 |
|
Maximilian Huettenrauch
|
2c8335f632
|
add render_mode option to mp_wrapper
|
2021-04-30 16:10:16 +02:00 |
|
Maximilian Huettenrauch
|
c2db2f8064
|
bug fixes
|
2021-04-23 12:47:55 +02:00 |
|
Maximilian Huettenrauch
|
ba0b612868
|
update readme and init
|
2021-04-23 12:16:19 +02:00 |
|
Maximilian Huettenrauch
|
db001c411f
|
updates
|
2021-04-23 11:37:42 +02:00 |
|
Maximilian Huettenrauch
|
e482fc09f0
|
wip
|
2021-04-21 10:45:34 +02:00 |
|
Maximilian Huettenrauch
|
f3d75b9a60
|
merge branches
|
2021-04-19 11:53:30 +02:00 |
|
Maximilian Huettenrauch
|
51e8503873
|
updates
|
2021-04-13 09:51:34 +02:00 |
|
Maximilian Huettenrauch
|
4673a8c13b
|
biac simple dmp env
|
2021-04-10 19:11:32 +02:00 |
|
Maximilian Huettenrauch
|
448ebcde95
|
holereach025 add success flag
|
2021-04-10 13:37:48 +02:00 |
|
Maximilian Huettenrauch
|
f6cef69225
|
holereach025
|
2021-04-10 13:25:08 +02:00 |
|
Maximilian Huettenrauch
|
1fd44616bf
|
updates
|
2021-04-08 19:00:48 +02:00 |
|
Maximilian Huettenrauch
|
f7c2f800ed
|
biac simple weights scale 0.5
|
2021-04-08 15:40:22 +02:00 |
|
Maximilian Huettenrauch
|
4308607a74
|
biac simple reward function update
|
2021-04-08 14:03:44 +02:00 |
|
Maximilian Huettenrauch
|
744f6eb747
|
updates
|
2021-04-08 12:02:45 +02:00 |
|
Maximilian Huettenrauch
|
4e72f10ee3
|
update on biac simple pmp width
|
2021-04-08 11:05:47 +02:00 |
|
Maximilian Huettenrauch
|
bafa28edca
|
holereacher pmp updates
|
2021-04-07 18:18:51 +02:00 |
|
Maximilian Huettenrauch
|
a3d365033a
|
updates
|
2021-03-30 18:01:13 +02:00 |
|
Maximilian Huettenrauch
|
948ca31bab
|
biac weight scale 0.2
|
2021-03-29 14:52:44 +02:00 |
|
ottofabian
|
dee2fad263
|
added asyc DMP example
|
2021-03-26 16:37:38 +01:00 |
|
ottofabian
|
0097fe4f99
|
Merge with stochastic search branch
|
2021-03-26 15:57:15 +01:00 |
|
ottofabian
|
6a7c6991bb
|
added balancing task
|
2021-03-26 15:32:50 +01:00 |
|
ottofabian
|
7ceadeff0a
|
refractoring of DMP environmets to fit gym interface better.
|
2021-03-26 14:05:16 +01:00 |
|
Maximilian Huettenrauch
|
6233c85904
|
update on holereacher reward
|
2021-03-22 15:28:50 +01:00 |
|
Fabian
|
89439f7532
|
updated incorrect angle normalization.
|
2021-03-22 15:25:22 +01:00 |
|
Maximilian Huettenrauch
|
a0692b1089
|
updates
|
2021-03-19 16:31:46 +01:00 |
|
Maximilian Huettenrauch
|
1d8b22245d
|
updates
|
2021-02-26 17:34:31 +01:00 |
|
Maximilian Huettenrauch
|
27d7da6774
|
biac weightscale change
|
2021-02-24 22:58:48 +01:00 |
|
Maximilian Huettenrauch
|
7e988758fe
|
updates
|
2021-02-24 15:37:54 +01:00 |
|
ottofabian
|
b7b5af03ba
|
added kl full cov projection and cov plots
|
2021-02-22 17:05:12 +01:00 |
|
Maximilian Huettenrauch
|
60e1673ee1
|
viapoint reacher reward bug fix
|
2021-02-19 16:17:55 +01:00 |
|
Maximilian Huettenrauch
|
1e3f036478
|
updates
|
2021-02-19 10:00:26 +01:00 |
|
Maximilian Huettenrauch
|
dd18a04df6
|
biac reward function update
|
2021-02-18 11:33:55 +01:00 |
|
Maximilian Huettenrauch
|
7ed22df778
|
update biac reward
|
2021-02-17 18:50:55 +01:00 |
|
Maximilian Huettenrauch
|
46fc642c36
|
updates
|
2021-02-17 17:48:05 +01:00 |
|
Maximilian Huettenrauch
|
420fe10506
|
biac normal cost
|
2021-02-16 18:47:08 +01:00 |
|
Maximilian Huettenrauch
|
7eef78d620
|
biac updates
|
2021-02-16 15:47:32 +01:00 |
|
Maximilian Huettenrauch
|
0916daf3b5
|
updates
|
2021-02-15 16:31:34 +01:00 |
|
Maximilian Huettenrauch
|
77d0cbd00a
|
updates
|
2021-02-15 09:03:19 +01:00 |
|
Maximilian Huettenrauch
|
95250af31c
|
added viapoint reacher
|
2021-02-12 17:12:40 +01:00 |
|
Maximilian Huettenrauch
|
708478c626
|
updates in biac
|
2021-02-11 16:19:57 +01:00 |
|
Maximilian Huettenrauch
|
13a292f0e0
|
updates
|
2021-02-11 12:32:32 +01:00 |
|
Maximilian Huettenrauch
|
c81378b9e7
|
support for contexts, policy classes, pd controller example, breaking changes etc
|
2021-02-11 10:49:57 +01:00 |
|
ottofabian
|
d026ebc427
|
added balancing to reacher
|
2021-02-09 17:07:52 +01:00 |
|
Maximilian Huettenrauch
|
07195fa2dc
|
lots of new stuff...
|
2021-02-05 17:10:03 +01:00 |
|
Maximilian Huettenrauch
|
cab2c249bb
|
started table tennis env
|
2021-01-21 09:42:04 +01:00 |
|
Maximilian Huettenrauch
|
2d9e7fb3eb
|
fixes in holereacher
|
2021-01-15 17:16:52 +01:00 |
|
Maximilian Huettenrauch
|
b7400c477d
|
updates
|
2021-01-14 17:10:03 +01:00 |
|
Maximilian Huettenrauch
|
104281fe16
|
changed from step to rollout method
|
2021-01-12 10:52:08 +01:00 |
|
Maximilian Huettenrauch
|
a8fcbd6fb0
|
dmp env wrappers initial
|
2021-01-11 16:08:42 +01:00 |
|
ottofabian
|
f171117d8f
|
fixed imports and first mpo version
|
2020-12-18 14:24:02 +01:00 |
|
ottofabian
|
b8f0c91a90
|
refractoring of projection layer, improved modularization of code
|
2020-12-11 09:46:35 +01:00 |
|
ottofabian
|
58131ef470
|
Added balancing reacher task and stochastic search task interface
|
2020-12-07 11:13:27 +01:00 |
|
ottofabian
|
741f1cb636
|
smaller changes
|
2020-11-03 11:26:06 +01:00 |
|
ottofabian
|
bac7a87b61
|
added Sparse Short version
|
2020-09-26 15:07:42 +02:00 |
|
ottofabian
|
d9f52194f7
|
reacher updates
|
2020-09-22 17:41:25 +02:00 |
|
ottofabian
|
8fc1210f1e
|
some new stuff
|
2020-09-19 17:47:20 +02:00 |
|
ottofabian
|
cbdd5d1854
|
removed action scaling
|
2020-09-08 12:43:14 +02:00 |
|
ottofabian
|
df4361564a
|
added max entropy RL and loading/testing of models
|
2020-09-04 13:35:05 +02:00 |
|
ottofabian
|
93e9c77356
|
removed EZPickle from SimpleReacher
|
2020-09-01 17:57:51 +02:00 |
|
ottofabian
|
a9d3e718bb
|
some changes to reward
|
2020-08-31 15:52:15 +02:00 |
|
ottofabian
|
3cc4d6e667
|
some changes to reward
|
2020-08-31 15:51:47 +02:00 |
|
ottofabian
|
7f4f52ab10
|
SimpleReacher state space changed
|
2020-08-31 11:26:32 +02:00 |
|
ottofabian
|
aec332ff0c
|
fixed some issues with SimpleReacher state space
|
2020-08-31 10:33:11 +02:00 |
|
ottofabian
|
2ff850328b
|
fixed some issues with SimpleReacher rendering
|
2020-08-31 10:18:59 +02:00 |
|
ottofabian
|
31156cec4d
|
added simple reacher task
|
2020-08-28 18:31:06 +02:00 |
|