gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-08-26 21:51:54 +02:00
Code Issues Projects Releases Wiki Activity
211 Commits 4 Branches 2 Tags
67faa80ea0dfe62da3215933c2c8da0aa814d4c4
Commit Graph
58 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
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 ad4d2c3053 add make stop_kubernetes 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
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 7c1f0dce4f include registry in image name 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
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
Zach Dwiel 747000647f add dockerfile 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 dc77c54ad9 add to gitignore 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
Zach Dwiel fb21251157 add horizontal scaling document 2018-10-23 16:34:38 -04:00
Zach Dwiel 673911ff7f very minor cleanup 2018-09-12 10:51:56 -04:00
Zach Dwiel 4fe9cba445 remove debug 2018-02-21 10:05:57 -05:00
Zach Dwiel eba900067c remove debug 2018-02-21 10:05:57 -05:00
Zach Dwiel d1bf83047c remove debug 2018-02-21 10:05:57 -05:00
Zach Dwiel ef46e194af remove unused commented code 2018-02-21 10:05:57 -05:00
Zach Dwiel d9303e731e remove python2 compatibility 2018-02-21 10:05:57 -05:00
Zach Dwiel ec68bd4959 make sure that for now observation spaces all include an observation key 2018-02-21 10:05:57 -05:00
Zach Dwiel 0740ebcdac by default assume state["observation"] is where the image for rendering can be found 2018-02-21 10:05:57 -05:00
Zach Dwiel f9f92a42fd cleanup debugging code 2018-02-21 10:05:57 -05:00
Zach Dwiel 86362683b1 comment 2018-02-21 10:05:57 -05:00
Zach Dwiel 8fc24a2bbe fix bc_agent 2018-02-21 10:05:57 -05:00
Zach Dwiel d8f5a35013 fix qr_dqn_agent 2018-02-21 10:05:57 -05:00
Zach Dwiel e1ad86417f fix n_step_q_agent 2018-02-21 10:05:57 -05:00
Zach Dwiel 5cf10e5f52 fix bug in ddpg 2018-02-21 10:05:57 -05:00
Zach Dwiel 8248caf35e fix more agents 2018-02-21 10:05:57 -05:00
Zach Dwiel 98f57a0d87 fix ddpg 2018-02-21 10:05:57 -05:00
Zach Dwiel 943e41ba58 fix nec_agent 2018-02-21 10:05:57 -05:00
Zach Dwiel ee6e0bdc3b fix keep_dims -> keepdims 2018-02-21 10:05:57 -05:00
Zach Dwiel 39a28aba95 fix clipped ppo 2018-02-21 10:05:57 -05:00
Zach Dwiel 85afb86893 temp commit 2018-02-21 10:05:57 -05:00
Zach Dwiel fff8c8f568 provide a helpful error message in the event that an exploration policy returns a vector of actions instead of a single action during value optimization agent 2018-01-20 14:11:24 -05:00
Zach Dwiel 40e5c628c6 add options for more verbose test errors 2018-01-16 22:08:46 -05:00
Zach Dwiel 8f026bb46f Merge pull request #42 from NervanaSystems/print_parameters 
provide a command line option which prints the tuning_parameters to stdout
 2018-01-11 11:28:24 -05:00
Zach Dwiel c7b11f1e9a provide a command line option which prints the tuning_parameters to stdout 2018-01-10 16:28:41 -05:00
Zach Dwiel 9b963c86d0 Merge pull request #41 from NervanaSystems/allow_direct_entry_point 
allow specifying gym environments via entry point syntax: module.package:class
 2018-01-10 12:18:12 -05:00
Zach Dwiel cc76a9ad70 allow specifying gym environments via entry point syntax: module.package:class 2018-01-10 10:14:23 -05:00
Zach Dwiel 499e78596a Merge pull request #38 from NervanaSystems/nec_lstm 
update nec and value optimization agents to work with recurrent middleware
 2018-01-08 14:01:34 -05:00
Zach Dwiel 6c79a442f2 update nec and value optimization agents to work with recurrent middleware 2018-01-05 20:16:51 -05:00
Zach Dwiel 7bdba396d2 Update add_env.md 2017-11-14 17:57:55 +02:00
Zach Dwiel 9ae2905a76 clean up input embeddings setup 2017-11-14 17:39:18 +02:00
Zach Dwiel aceddfadc9 Merge pull request #3 from cclauss/patch-1 
Simplify w/ dict.get() default value, ternary if
 2017-10-22 20:46:36 -04:00
Zach Dwiel 6fec9f972f Merge pull request #7 from zac-hopkinson/master 
Fixes installer issues #5 and #6
 2017-10-22 20:42:57 -04:00