gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-04-10 07:03:40 +02:00
Code Issues Projects Releases Wiki Activity

Commit Graph

  • 2d5688c737 additional benchmarks for a3c and dqn Itai Caspi 2018-08-16 20:01:35 +03:00
  • 1de04d6fee updated gifs in README + fix for multiworker crashes + improved Atari DQN and Dueling DDQN presets Itai Caspi 2018-08-16 18:23:32 +03:00
  • 8f99409387 updating algorithms.png for README Gal Leibovich 2018-08-16 16:46:26 +03:00
  • ab5a81c7ee fix for dumping movies, without rendering, for pendulum_with_goals Gal Leibovich 2018-08-14 18:13:44 +03:00
  • e783157b15 Update README.md Gal Leibovich 2018-08-14 16:16:41 +03:00
  • 824fdeee59 Update README with new coach aliases Itai Caspi 2018-08-14 14:36:41 +03:00
  • 7a76d63da4 Update README.md Gal Leibovich 2018-08-13 17:19:47 +03:00
  • 19ca5c24b1 pre-release 0.10.0 Gal Novik 2018-08-13 17:11:34 +03:00
  • d44c329bb8 Update README.md Itai Caspi 2018-06-25 17:46:01 +03:00
  • cfd4fe0faf Update README.md Itai Caspi 2018-06-25 17:43:15 +03:00
  • 2807c29f27 fix for measurements in the initial state (fix for DFP) Gal Leibovich 2018-05-29 16:47:38 +03:00
  • 7725dabc86 checkpoints bug fix itaicaspi-intel 2018-05-26 17:49:13 +03:00
  • 462c6e314b bug fix in nec checkpoint saving itaicaspi-intel 2018-05-24 15:15:33 +03:00
  • d302168c8c Parallel agents fixes (#95) Itai Caspi 2018-05-24 14:24:19 +03:00
  • 6c0b59b4de constraining gym installation to version 0.9.4 itaicaspi-intel 2018-05-22 11:01:58 +03:00
  • 7cbbb8f718 Removed carla environ wc Roman Dobosz 2018-05-10 09:24:40 +02:00
  • cd6376f821 removing doom env Roman Dobosz 2018-05-10 09:19:32 +02:00
  • 5d47368972 Celaning up coach code + removing play/Human agent Roman Dobosz 2018-05-10 09:06:10 +02:00
  • a57b7004a8 updating dashboard itaicaspi-intel 2018-05-09 09:26:15 +03:00
  • 50d38b4b98 Moved main module to cli Roman Dobosz 2018-05-08 11:01:57 +02:00
  • dafdb05a7c bug fixes for clippedppo and checkpoints Gal Novik 2018-04-30 15:13:29 +03:00
  • 26a2f94f43 Added pyyaml dependecy to setup/requirements Roman Dobosz 2018-04-27 14:48:43 +02:00
  • 676c69e391 Moved coach to its top level module. Roman Dobosz 2018-04-25 12:03:36 +02:00
  • 7e61bb5685 Removed unnecessary files Roman Dobosz 2018-04-25 11:58:57 +02:00
  • 5c53f9be02 Added missing imports, correct usages imports Roman Dobosz 2018-04-24 13:33:10 +02:00
  • 42a9ec132d Merge branch 'master' into imports Roman Dobosz 2018-04-24 07:43:04 +02:00
  • f31159aad6 bug fixes for carla environment (#93) Itai Caspi 2018-04-23 11:13:24 +03:00
  • 52eb159f69 multiple bug fixes in dealing with measurements + CartPole_DFP preset (#92) Itai Caspi 2018-04-23 10:44:46 +03:00
  • 5d5562bf62 moving the docs to github itaicaspi-intel 2018-04-23 09:14:20 +03:00
  • 1b095aeeca Cleanup imports. Roman Dobosz 2018-04-12 19:46:32 +02:00
  • cafa152382 update requirements to have valid tornado version (#84) jtoy 2018-04-02 04:21:35 -07:00
  • efc6e67a45 update evaluation periods running_stats_fix itaicaspi-intel 2018-03-19 17:48:57 +02:00
  • 24a0f24279 adding pickling of running_stats and updating the beta entropy for ClippedPPO itaicaspi-intel 2018-03-19 14:37:05 +02:00
  • a7206ed702 Multiple improvements and bug fixes (#66) Itai Caspi 2018-02-26 12:29:07 +02:00
  • 4fe9cba445 remove debug Zach Dwiel 2018-02-20 13:04:52 -05:00
  • eba900067c remove debug Zach Dwiel 2018-02-20 11:57:16 -05:00
  • d1bf83047c remove debug Zach Dwiel 2018-02-20 11:56:50 -05:00
  • ef46e194af remove unused commented code Zach Dwiel 2018-02-20 11:55:34 -05:00
  • d9303e731e remove python2 compatibility Zach Dwiel 2018-02-20 11:54:38 -05:00
  • ec68bd4959 make sure that for now observation spaces all include an observation key Zach Dwiel 2018-02-20 11:51:27 -05:00
  • 0740ebcdac by default assume state["observation"] is where the image for rendering can be found Zach Dwiel 2018-02-20 11:45:35 -05:00
  • f9f92a42fd cleanup debugging code Zach Dwiel 2018-02-20 11:43:56 -05:00
  • 86362683b1 comment Zach Dwiel 2018-02-20 11:39:20 -05:00
  • 8fc24a2bbe fix bc_agent Zach Dwiel 2018-02-16 20:39:00 -05:00
  • d8f5a35013 fix qr_dqn_agent Zach Dwiel 2018-02-16 20:32:50 -05:00
  • e1ad86417f fix n_step_q_agent Zach Dwiel 2018-02-16 20:25:33 -05:00
  • 5cf10e5f52 fix bug in ddpg Zach Dwiel 2018-02-16 20:18:03 -05:00
  • 8248caf35e fix more agents Zach Dwiel 2018-02-16 20:06:51 -05:00
  • 98f57a0d87 fix ddpg Zach Dwiel 2018-02-16 15:47:16 -05:00
  • 943e41ba58 fix nec_agent Zach Dwiel 2018-02-16 13:36:14 -05:00
  • ee6e0bdc3b fix keep_dims -> keepdims Zach Dwiel 2018-02-16 13:30:31 -05:00
  • 39a28aba95 fix clipped ppo Zach Dwiel 2018-02-16 13:22:10 -05:00
  • 85afb86893 temp commit Zach Dwiel 2018-02-16 09:35:58 -05:00
  • 16c5032735 fix for tensorboard visualization slowing execution even when it is off Gal Leibovich 2018-02-17 12:42:59 +02:00
  • 72d34f4063 adding a flag to prevent summary Itai Caspi 2018-02-14 12:30:25 +02:00
  • 55c8c87afc allow visualizing the observation + bug fixes to coach summary Itai Caspi 2018-02-13 18:47:24 +02:00
  • 5d1a2bc392 Adding a summary when exiting coach Itai Caspi 2018-02-12 16:47:47 +02:00
  • ba96e585d2 appending csv's from logger instead of rewriting them Itai Caspi 2018-02-12 01:33:43 +02:00
  • 569ca39ce6 Dashboard color selection + removing old legend Itai Caspi 2018-02-09 16:51:21 +02:00
  • 8a4383e86f Added an improved legend to dashboard Itai Caspi 2018-02-08 18:46:40 +02:00
  • b071599cb0 updating intel optimized tensorflow to version 1.4 Itai Caspi 2018-02-07 15:18:03 +02:00
  • 462fe9796b several bug fixes in dashboard Itai Caspi 2018-02-07 14:46:35 +02:00
  • 4025496783 Setting tensorflow-gpu version to 1.4.1 (1.5.0 is not tested yet) galleibo-intel 2018-02-05 15:47:06 +02:00
  • 7c8962c991 adding support in tensorboard (#52) Gal Leibovich 2018-02-05 15:21:49 +02:00
  • a8d5fb7bdf Added a table of contents to the README Itai Caspi 2018-01-27 14:31:53 +02:00
  • 522c837e76 Update README.md Itai Caspi 2018-01-22 12:15:23 +02:00
  • 43821c9630 adding the selu activation Itai Caspi 2018-01-21 12:15:21 +02:00
  • 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 Zach Dwiel 2018-01-11 11:43:37 -05:00
  • 40e5c628c6 add options for more verbose test errors Zach Dwiel 2018-01-16 17:12:50 -05:00
  • 8f026bb46f Merge pull request #42 from NervanaSystems/print_parameters Zach Dwiel 2018-01-11 11:28:24 -05:00
  • c7b11f1e9a provide a command line option which prints the tuning_parameters to stdout Zach Dwiel 2018-01-10 16:28:41 -05:00
  • 9b963c86d0 Merge pull request #41 from NervanaSystems/allow_direct_entry_point Zach Dwiel 2018-01-10 12:18:12 -05:00
  • cc76a9ad70 allow specifying gym environments via entry point syntax: module.package:class Zach Dwiel 2018-01-10 10:14:23 -05:00
  • 42f68f2e8a update the README with contact mail + small reformatting Itai Caspi 2018-01-09 13:08:23 +02:00
  • eeb3ec5497 fixed the LSTM middleware initialization Itai Caspi 2017-12-30 15:18:09 +02:00
  • b435c6d2d7 updated the links to the new Intel AI website Itai Caspi 2018-01-09 10:25:06 +02:00
  • 499e78596a Merge pull request #38 from NervanaSystems/nec_lstm Zach Dwiel 2018-01-08 14:01:34 -05:00
  • 29857412b3 Add force flag to library symbolic link Justin 2018-01-08 11:33:12 +01:00
  • 6c79a442f2 update nec and value optimization agents to work with recurrent middleware Zach Dwiel 2017-11-03 13:58:42 -07:00
  • 645d9d47a9 Adding bibtex to the README Itai Caspi 2018-01-03 21:11:57 +02:00
  • 93a54c7e8e Added a link to the 2nd blog post Itai Caspi 2017-12-20 17:18:49 +02:00
  • 9e59d1960e bug fix for dumping gifs from doom Itai Caspi 2017-12-20 13:09:41 +02:00
  • 37e317682b allow missing carla environment and missing matplotlib package Zach Dwiel 2017-12-19 23:03:19 -05:00
  • 125c7ee38d Release 0.9 v0.9.0 Itai Caspi 2017-12-19 19:27:16 +02:00
  • 11faf19649 QR-DQN bug fix and imporvements (#30) Itai Caspi 2017-11-29 14:01:59 +02:00
  • 7bdba396d2 Update add_env.md Zach Dwiel 2017-11-04 22:12:59 -04:00
  • 9ae2905a76 clean up input embeddings setup Zach Dwiel 2017-11-03 13:51:02 -07:00
  • 1ff0da2165 bug fix - fixed an issue with gifs dumping and bumped up Pillow version to 4.3.0 Itai Caspi 2017-11-13 12:22:32 +02:00
  • acd2b78a9e Update README.md Miguel Morales 2017-11-11 07:47:47 -07:00
  • 8d9ee4ea2b bug fix - fixed C51 presets hyperparameters Itai Caspi 2017-11-10 13:22:00 +02:00
  • 3c330768f0 Fix for NEC not saving the DND when saving a model galleibo-intel 2017-11-09 19:13:23 +02:00
  • f5d645d8a6 resize training curves images Itai Caspi 2017-11-09 09:13:12 +02:00
  • 8ee9e46083 fixing some typos in the benchmarks README Itai Caspi 2017-11-09 08:58:52 +02:00
  • c798be7bfb added training curves for some of the presets Itai Caspi 2017-11-09 08:54:20 +02:00
  • 84e536d371 Fix std calculation using unbiased estimation in sharing stat mode. cxx 2017-11-07 13:49:33 +08:00
  • f47b8092af fix for intel optimized tensorflow on distributed runs + adding coach_env to .gitignore galleibo-intel 2017-11-06 19:41:32 +02:00
  • b40259c61a bug fix - remove import warning when everything was imported successfully + changed global step api to match TF 1.4 Itai Caspi 2017-11-06 17:28:13 +02:00
  • fd103a7b69 updated the algorithms diagram with QR-DQN Itai Caspi 2017-11-01 15:24:54 +02:00
  • a8bce9828c new feature - implementation of Quantile Regression DQN (https://arxiv.org/pdf/1710.10044v1.pdf) API change - Distributional DQN renamed to Categorical DQN Itai Caspi 2017-11-01 15:09:07 +02:00
  • 1ad6262307 bug fix - correcting the evaluation exploration control parameter logging Itai Caspi 2017-10-31 13:50:40 +02:00