 Ajay Deshpande
|
a2e57a44f1
|
Getting only the model_checkpoint_path files
|
2018-10-23 16:54:43 -04:00 |
|
|
Ajay Deshpande
|
052bbc8f19
|
Adding lock in s3
|
2018-10-23 16:54:43 -04:00 |
|
|
Balaji Subramaniam
|
844a5af831
|
Make distributed coach work end-to-end.
- With data store, memory backend and orchestrator interfaces.
|
2018-10-23 16:54:43 -04:00 |
|
|
Zach Dwiel
|
9f92064e67
|
cleanup graph_manager:act
|
2018-10-23 16:53:32 -04:00 |
|
|
Zach Dwiel
|
b5305bd075
|
update dockerfile
|
2018-10-23 16:52:16 -04:00 |
|
|
Zach Dwiel
|
950f261201
|
extract method all_presets
|
2018-10-23 16:52:16 -04:00 |
|
|
Zach Dwiel
|
ed3a3b39be
|
add comments
|
2018-10-23 16:52:16 -04:00 |
|
|
Balaji Subramaniam
|
1c238b4c60
|
Added data store backend. (#17)
* Added data store backend.
* Add NFS implementation for Kubernetes.
* Added S3 data store implementation.
* Addressed review comments.
|
2018-10-23 16:52:16 -04:00 |
|
|
Ajay Deshpande
|
6b2de6ba6d
|
Adding initial interface for backend and redis pubsub (#19)
* Adding initial interface for backend and redis pubsub
* Addressing comments, adding super in all memories
* Removing distributed experience replay
|
2018-10-23 16:51:48 -04:00 |
|
|
Zach Dwiel
|
a54ef2757f
|
ignore deprecation warnings in test logging
|
2018-10-23 16:51:48 -04:00 |
|
|
Zach Dwiel
|
acc7f70de3
|
enumerate each preset as its own test
|
2018-10-23 16:51:48 -04:00 |
|
|
Zach Dwiel
|
67faa80ea0
|
allow custom number of training steps
|
2018-10-23 16:51:48 -04:00 |
|
|
Zach Dwiel
|
d69332efd4
|
fixed bug in training worker
|
2018-10-23 16:51:48 -04:00 |
|
|
Zach Dwiel
|
cd733b2404
|
add support for running kubernetes orchestrator from behind proxy
|
2018-10-23 16:51:48 -04:00 |
|
|
Zach Dwiel
|
5e85a0f972
|
use the number of heat up steps specified in schedule parameters
|
2018-10-23 16:51:48 -04:00 |
|
|
Ajay Deshpande
|
98850464cc
|
Adding nfs pv, pvc, waiting for memory to be full
|
2018-10-23 16:50:48 -04:00 |
|
|
Zach Dwiel
|
13d81f65b9
|
add redis options to training worker
|
2018-10-23 16:47:46 -04:00 |
|
|
Zach Dwiel
|
04f32a0f02
|
add heatup step to training worker
|
2018-10-23 16:47:46 -04:00 |
|
|
Zach Dwiel
|
0812a94fbd
|
first pass at kubernetes
|
2018-10-23 16:47:46 -04:00 |
|
|
Zach Dwiel
|
3328b25549
|
reenable redis; better error message
|
2018-10-23 16:47:46 -04:00 |
|
|
Zach Dwiel
|
009cf670f3
|
fix simple typos; temporarily disable redis in rollout worker
|
2018-10-23 16:47:46 -04:00 |
|
|
Zach Dwiel
|
f5b7122d56
|
weight for checkpoint before trying to start rollout worker
|
2018-10-23 16:47:46 -04:00 |
|
|
Zach Dwiel
|
4352d6735d
|
add training worker
|
2018-10-23 16:47:46 -04:00 |
|
|
Ajay Deshpande
|
28926bf2a4
|
Changing parameters
|
2018-10-23 16:47:46 -04:00 |
|
|
Ajay Deshpande
|
c2991819b4
|
Adding right arguments to the agent
|
2018-10-23 16:46:04 -04:00 |
|
|
Ajay Deshpande
|
ce9838a7d6
|
Adding kubernetes orchestrator for rollouts, adding requirements for incremental docker builds
|
2018-10-23 16:46:04 -04:00 |
|
|
Zach Dwiel
|
6541bc76b9
|
working checkpoints
|
2018-10-23 16:41:57 -04:00 |
|
|
Zach Dwiel
|
433bc3e27b
|
standardizing variable access
|
2018-10-23 16:40:33 -04:00 |
|
|
Zach Dwiel
|
e34b9ae9cf
|
allow specifying preset as a commandline parameter to rollout worker
|
2018-10-23 16:40:33 -04:00 |
|
|
Zach Dwiel
|
3714d8ec80
|
extract functions display_all_presets_and_exit, expand_preset
|
2018-10-23 16:40:33 -04:00 |
|
|
Ajay Deshpande
|
21f8ca3978
|
Removing comments and pytests
|
2018-10-23 16:40:33 -04:00 |
|
|
Ajay Deshpande
|
5a54f67a63
|
Adding distributed experience replay
|
2018-10-23 16:40:33 -04:00 |
|
|
Zach Dwiel
|
bc664c4169
|
add the first pass of rollout_worker.py
|
2018-10-23 16:40:33 -04:00 |
|
|
Zach Dwiel
|
61ed6b8ce4
|
add better defaults to TaskParameters
|
2018-10-23 16:40:33 -04:00 |
|
|
Zach Dwiel
|
5758c2f23e
|
typo; increased detail in comment
|
2018-10-23 16:35:06 -04:00 |
|
|
Zach Dwiel
|
a1295d16b3
|
first pass that transition collection interface
|
2018-10-23 16:35:06 -04:00 |
|
|
Zach Dwiel
|
9f1f9e5ab4
|
replace ExperienceReplay._num_transitions with len(ExperienceReplay.transitions)
|
2018-10-23 16:34:38 -04:00 |
|
|
Zach Dwiel
|
cccfe88f9b
|
remove unused method: update_last_transition_info
|
2018-10-23 16:34:38 -04:00 |
|
|
Gal Leibovich
|
5a8da90d32
|
bug-fix for dumping movies (+ small refactoring and rename 'VideoDumpMethod -> 'VideoDumpFilter')
|
2018-10-21 17:29:10 +03:00 |
|
|
Shadi Endrawis
|
364168490f
|
checkpointing fix
|
2018-10-07 20:06:08 +03:00 |
|
|
Shadi Endrawis
|
f7990d4003
|
trace tests update
|
2018-10-02 17:55:16 +03:00 |
|
|
Shadi Endrawis
|
51726a5b80
|
network_imporvements branch merge
|
2018-10-02 13:43:36 +03:00 |
|
|
Gal Leibovich
|
72ea933384
|
bug-fix for clipped_ppo not logging several signals + small cleanup
|
2018-10-02 14:22:37 +03:00 |
|
|
itaicaspi-intel
|
73cc6e39d0
|
bug fix for clipped ppo for discrete controls
|
2018-09-18 10:40:53 +03:00 |
|
|
Gal Novik
|
abaa58b559
|
human agent will exit when human control not supported by environment; jupyter notebooks fixes
|
2018-09-17 16:00:00 +03:00 |
|
|
itaicaspi-intel
|
bb76c5c726
|
CARLA cleanups + calculating the distance to goal
|
2018-09-16 16:37:04 +03:00 |
|
|
itaicaspi-intel
|
6797824892
|
bug fixes in the CARLA dataset downloader and extractor
|
2018-09-16 14:27:22 +03:00 |
|
|
itaicaspi-intel
|
23a9f00e28
|
fix for human control
|
2018-09-16 12:43:15 +03:00 |
|
|
itaicaspi-intel
|
cf892463e2
|
updated CARLA to allow using actions of size 3 + automatic downloading of the CARLA imitation dataset
|
2018-09-16 12:07:11 +03:00 |
|
|
itaicaspi-intel
|
f8d3574b8c
|
updated CARLA to allow the usage of predefined experiment suites
|
2018-09-14 18:07:24 +03:00 |
|