Sina Afrooze
95b4fc6888
Added ability to switch between tensorflow and mxnet using -f commandline argument. ( #48 )
...
NOTE: tensorflow framework works fine if mxnet is not installed in env, but mxnet will not work if tensorflow is not installed because of the code in network_wrapper.
2018-10-30 15:29:34 -07:00
Sina Afrooze
2046358ab0
Add docstring for architecture ( #47 )
...
- Removed get_model() from architecture because it is only implementation detail of architecture.
2018-10-30 11:02:37 +02:00
Thom Lane
324c67d614
Bug fix: Removed reference to args which is out of scope. Conditioning now performed one level above. ( #54 )
2018-10-29 22:29:22 -07:00
Sina Afrooze
a888226641
Move embedder, middleware, and head parameters to framework agnostic modules. ( #45 )
...
Part of #28
2018-10-29 14:46:40 -07:00
Ajay Deshpande
16b3e99f37
Setup basic CI flow ( #38 )
...
Adds automated running of unit, integration tests (and optionally longer running tests)
2018-10-24 18:27:58 -07:00
Zach Dwiel
2cc6abc3c4
update CartPole_PPO not addressed during rebase ( #41 )
2018-10-24 16:58:25 -07:00
zach dwiel
f835ac902c
fix renaming: save_checkpoint_sec -> checkpoint_save_secs
2018-10-24 10:52:18 -04:00
Ajay Deshpande
78cf25c09a
Removing mjkey, should be injected from env var
2018-10-23 19:59:02 -04:00
Ajay Deshpande
fb2721fffa
Removing comments
2018-10-23 19:59:02 -04:00
Ajay Deshpande
9a30c26469
Adding improvements
2018-10-23 19:59:02 -04:00
zach dwiel
3ba0df7d07
update GraphManager.act specified return type
2018-10-23 19:58:17 -04:00
zach dwiel
def76b4cc6
update CartPole_PPO
2018-10-23 19:58:17 -04:00
zach dwiel
3e5e5475de
update training worker
2018-10-23 19:58:17 -04:00
zach dwiel
430ca198e5
convert golden tests into pytest format
2018-10-23 19:58:17 -04:00
zach dwiel
787ab42578
remove extra call to super().store_episode
2018-10-23 19:58:17 -04:00
Zach Dwiel
7220283653
add len(Episode)
2018-10-23 19:58:17 -04:00
Zach Dwiel
700a175902
rename save_checkpoint_secs -> checkpoint_save_secs
2018-10-23 17:10:58 -04:00
Zach Dwiel
9804b033a2
rename save_checkpoint_dir -> checkpoint_save_dir
2018-10-23 17:10:58 -04:00
Zach Dwiel
201a2237a1
restructure looping mechanism inGraphManager
2018-10-23 17:10:58 -04:00
Zach Dwiel
52560a2aae
introduce property GraphManager.current_step_counter
2018-10-23 17:10:04 -04:00
Zach Dwiel
776c94d551
reorder methods in GraphManager
2018-10-23 17:10:04 -04:00
Zach Dwiel
496a516de1
rename GraphManager.sync_graph -> sync
2018-10-23 17:08:29 -04:00
Zach Dwiel
5fee48dcfd
remove argument keep_networks_in_sync from GraphManager.act, and move this feature into the only place that activated it: GraphManager.train_and_act
2018-10-23 17:08:29 -04:00
Zach Dwiel
b2d864a5bd
remove out of date documentation
2018-10-23 17:08:29 -04:00
Zach Dwiel
d32d909238
move only invocation of GraphManager.handle_episode_ended inline
2018-10-23 17:08:29 -04:00
Zach Dwiel
18d84c5037
remove unnecessary timers from GraphManager
2018-10-23 16:58:17 -04:00
Zach Dwiel
cd30efe52e
remove unnecessary test result is None in GraphManager.act
2018-10-23 16:57:43 -04:00
Zach Dwiel
35d67cbd9b
use phase context in GraphManager.evaluate
2018-10-23 16:57:43 -04:00
Zach Dwiel
d3c341147e
simplify GraphManager.act by removing arguments: continue_until_game_over and return_on_game_over
2018-10-23 16:57:43 -04:00
Zach Dwiel
8be980912c
fixed typo from earlier commit
2018-10-23 16:57:43 -04:00
Zach Dwiel
fbaf19543e
capture stdout during preset tests
2018-10-23 16:57:43 -04:00
Zach Dwiel
517aac163a
introduce graph_manager.phase_context; make sure that calls to graph_manager.train automatically set training phase
2018-10-23 16:57:43 -04:00
Zach Dwiel
7382a142bb
remove unused steps parameter from GraphManager.train
2018-10-23 16:57:06 -04:00
Zach Dwiel
97f608ee5e
reorder failing presets
2018-10-23 16:57:05 -04:00
Zach Dwiel
ad68fa263d
remove property GraphManager.training_start_time
2018-10-23 16:57:05 -04:00
Zach Dwiel
bfc320cf83
disable failing tests for now
2018-10-23 16:57:05 -04:00
Zach Dwiel
01f3a0594b
remove return values from GraphManager.act
2018-10-23 16:57:05 -04:00
Zach Dwiel
b02f269464
graph_manager:heatup uses total_steps_counters looping mechanism like other loops. graph_manager:act no longer needs to return any values
2018-10-23 16:57:05 -04:00
Balaji Subramaniam
ca9015d8b1
Make NFS work end-to-end.
2018-10-23 16:55:37 -04:00
Ajay Deshpande
fb1039fcb5
Checkpoint and evaluation optimizations
2018-10-23 16:55:37 -04:00
Ajay Deshpande
b285a02023
Adding parameteres, checking transitions before training
2018-10-23 16:55:37 -04:00
Ajay Deshpande
0f46877d7e
Adding steps and waiting for new checkpoint
2018-10-23 16:55:37 -04:00
Ajay Deshpande
0e121c5762
Ignoring redis sub if testing
2018-10-23 16:55:37 -04:00
Ajay Deshpande
7f00235ed5
waiting for a new checkpoint if it's available
2018-10-23 16:54:43 -04:00
Ajay Deshpande
5eac0102de
Changing exception type
2018-10-23 16:54:43 -04:00
Ajay Deshpande
a7f5442015
Adding should_train helper and should_train in graph_manager
2018-10-23 16:54:43 -04:00
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
