Commit graph

Select branches

Hide pull requests

master

#1

#2

#3

#4

#5

Mono Color

• cb87105305 Work towards simplifying ReplayMemory master Brandon Rozek 2020-04-14 16:02:59 -04:00
• c6172f309d Made Logger global Brandon Rozek 2020-04-14 15:24:48 -04:00
• 1f7c6f10ab Used standard library definition Brandon Rozek 2020-04-14 14:21:31 -04:00
• 8fa4691511 PEP8 Conformance Brandon Rozek 2020-04-14 14:16:14 -04:00
• 9b81188a77
  Update LICENSE Brandon Rozek 2020-03-29 14:10:07 -04:00
• b12f54e3cd
  Delete license.md Brandon Rozek 2020-03-29 14:07:29 -04:00
• 112acf9085
  Create LICENSE Brandon Rozek 2020-03-29 14:07:06 -04:00
• a667b3734b Merge branch 'master' of github.com:Brandon-Rozek/rltorch Brandon Rozek 2020-03-23 19:57:21 -04:00
• 838062813a Better handling of demonstration data Brandon Rozek 2020-03-23 19:57:05 -04:00
• 4c6dc0a2ea Added network documentation Brandon Rozek 2020-03-20 20:16:29 -04:00
• 5e7de5bed7 Documentation for logging utility Brandon Rozek 2020-03-20 19:38:45 -04:00
• a47f3f6037 Seed documentation Brandon Rozek 2020-03-20 19:38:35 -04:00
• 1cad98fcf9 Created documentation for memory module Brandon Rozek 2020-03-20 19:31:09 -04:00
• 711c2e8dd1 Cleaned up scheduler docs Brandon Rozek 2020-03-20 19:30:56 -04:00
• 720bb1b051 Documented scheduler module Brandon Rozek 2020-03-20 17:59:56 -04:00
• ea62ccf389 Added templates for unit testing and sphinx documentation Brandon Rozek 2020-03-15 14:27:56 -04:00
• 2e01bc16ea
  Merge pull request #5 from Brandon-Rozek/dependabot/pip/tensorflow-1.15.2 Brandon Rozek 2020-03-15 13:16:03 -04:00
• c6ca2a4cfe
  Bump tensorflow from 1.15.0 to 1.15.2 dependabot[bot] 2020-01-28 22:34:13 +00:00
• 557c0f689a
  Merge pull request #4 from Brandon-Rozek/dependabot/pip/urllib3-1.24.2 Brandon Rozek 2020-01-02 23:50:58 -05:00
• 8323b1b073
  Bump urllib3 from 1.24.1 to 1.24.2 dependabot[bot] 2020-01-03 04:48:59 +00:00
• 0c7640fea1
  Merge pull request #1 from Brandon-Rozek/dependabot/pip/werkzeug-0.15.3 Brandon Rozek 2020-01-02 23:48:21 -05:00
• d8d1a0a5e9
  Merge pull request #2 from Brandon-Rozek/dependabot/pip/pillow-6.2.0 Brandon Rozek 2020-01-02 23:48:09 -05:00
• 3c09867fb2
  Merge pull request #3 from Brandon-Rozek/dependabot/pip/tensorflow-1.15.0 Brandon Rozek 2020-01-02 23:47:54 -05:00
• 35f57a3f22
  Bump tensorflow from 1.12.0 to 1.15.0 dependabot[bot] 2019-12-16 21:27:03 +00:00
• 3217c76a79 DQfD memory was adjusted to actually update the weights in the priority trees, fixing a bug in the sampling Brandon Rozek 2019-11-17 19:50:49 -05:00
• 23532fc372 Added a way to cap the number of demonstrations that are kept in the buffer Brandon Rozek 2019-11-17 18:29:12 -05:00
• 038d406d0f Fixed errors with n-step returns Brandon Rozek 2019-11-13 22:56:27 -05:00
• ed62e148d5 Initial implementation of n-step loss Brandon Rozek 2019-11-11 10:24:40 -05:00
• 07c90a09f9 Fixed scoping error with Transitions Brandon Rozek 2019-11-04 12:09:09 -05:00
• ad75539776 Implemented components necessary for Deep Q Learning from Demonstrations Brandon Rozek 2019-11-04 07:44:39 -05:00
• 17391c7467 First draft of Deep Q Learning From Demonstrations Brandon Rozek 2019-10-31 20:54:52 -04:00
• 6b2b6da9e6
  Bump pillow from 5.4.1 to 6.2.0 dependabot[bot] 2019-10-22 22:14:02 +00:00
• 324fa5c667
  Bump werkzeug from 0.14.1 to 0.15.3 dependabot[bot] 2019-10-21 18:14:40 +00:00
• 559efa38b0 Corrected for numba deprecation Enable the ability to render out scenes to play back data Brandon Rozek 2019-09-19 07:57:39 -04:00
• a99ca66b4f Fixed multiprocessing with CUDA. Added entropy importance as a config option. Brandon Rozek 2019-09-18 07:26:32 -04:00
• 9d32a9edd1 Merge branch 'master' of https://github.com/Brandon-Rozek/rltorch Brandon Rozek 2019-09-13 20:00:13 -04:00
• da83f1470c Some work on multiprocessing evolutionary strategies from last semester Brandon Rozek 2019-09-13 19:53:19 -04:00
• 7aa698c349 Added save and load functionality Brandon Rozek 2019-09-13 19:49:04 -04:00
• dcf7cce30d Flush out print text so I can keep track of the rewards by SSHing in Brandon Rozek 2019-09-13 19:48:51 -04:00
• 912e3d42cb Added new OpenAI Baseline Wrappers Brandon Rozek 2019-09-13 19:48:24 -04:00
• 6d3a78cd20 Added parallel version of ES Brandon Rozek 2019-03-30 16:33:40 -04:00
• 9ad63a6921 Added license Brandon Rozek 2019-03-30 16:32:57 -04:00
• b2f5220585 Made sure the reward_batch is float across different agents Brandon Rozek 2019-03-14 10:43:14 -04:00
• cdfd3ab6b9 Playing around with QEP Brandon Rozek 2019-03-14 00:53:51 -04:00
• 8683b75ad9 Corrected gamma multiplication Brandon Rozek 2019-03-04 22:04:13 -05:00
• 190eb1f0c4 Correct discount_rewards function to only multiply with gamma throughout Brandon Rozek 2019-03-04 21:59:02 -05:00
• 11d99df977 Added improvements to the REINFORCE algorithm Brandon Rozek 2019-03-04 17:10:24 -05:00
• a59f84b446 Cleaned up scripts, added more comments Brandon Rozek 2019-03-04 17:09:46 -05:00
• e42f5bba1b Corrected A2C and PPO to train at the end of an episode Brandon Rozek 2019-03-01 21:04:13 -05:00
• 1958fc7c7e Corrected device when constructing fitness tensor Brandon Rozek 2019-02-28 14:41:34 -05:00
• 9740c40527 d.sample returns a tensor, so we stack them to not lose the device Brandon Rozek 2019-02-28 14:30:49 -05:00
• 714443192d Added entropy into QEP (1% of loss) Made random numbers generated in ESNetwork happen in the same device Brandon Rozek 2019-02-28 12:17:35 -05:00
• 76a044ace9 Added Evolutionary Strategies Network and added more example scripts Brandon Rozek 2019-02-27 09:52:28 -05:00
• 26084d4c7c Added PPOAgent and A2CAgent to the agents submodule. Also made some small changes to how memories are queried Brandon Rozek 2019-02-19 20:54:30 -05:00
• 21b820b401 Implemented REINFORCE into the library Brandon Rozek 2019-02-16 20:30:27 -05:00
• 14ba64d525 Added a single process environment runner. Also added an example for using such class. Brandon Rozek 2019-02-16 18:15:45 -05:00
• 736e73a1f7 Took away explicit deleting since the next_state variable gets used in another slot Brandon Rozek 2019-02-14 22:01:13 -05:00
• 2caf869fd6 Added numba as a dependency and decorated the Prioiritzed Replay function Brandon Rozek 2019-02-14 21:42:31 -05:00
• 19a859a4f6 If memory or logger does not exist, then don't create those shared memory structures Brandon Rozek 2019-02-14 21:06:44 -05:00
• 460d4c05c1 Fixed EnvironmentRun to be properly multiprocess. Fixed the prioirity of bad states to be the smallest [TODO] Make EnvironmentEpisode properly multiprocess Brandon Rozek 2019-02-13 23:47:37 -05:00
• 115543d201 Fixed parallel implementation of getting experiences by using a queue Brandon Rozek 2019-02-13 00:36:23 -05:00
• 5094ed53af Updated examples to have new features Brandon Rozek 2019-02-11 10:23:11 -05:00
• fe97a9b78d Corrected typo Brandon Rozek 2019-02-11 00:00:34 -05:00
• be637664e7 Added collections import Brandon Rozek 2019-02-10 23:59:29 -05:00
• b2ab2ee132 Implemented epsilon as a scheduler Brandon Rozek 2019-02-10 23:56:21 -05:00
• 04e54cddc2 Sends importance weights into correct device for prioiritized replay Brandon Rozek 2019-02-10 23:16:44 -05:00
• 013d40a4f9 Implemented Schedulers and Prioritized Replay Brandon Rozek 2019-02-10 23:11:53 -05:00
• 8c78f47c0c Added missing parameter Brandon Rozek 2019-02-03 21:57:27 -05:00
• f1a52cf77b Added missing dependency Brandon Rozek 2019-02-03 21:55:08 -05:00
• 0a6f1e73f3 Fixed another mismatched device error Brandon Rozek 2019-02-03 00:53:13 -05:00
• e62385b574 Fixed not having self. Brandon Rozek 2019-02-03 00:51:24 -05:00
• 03455accc8 Attempting to see if this fixes the mismatched devices error Brandon Rozek 2019-02-03 00:49:47 -05:00
• 9cd3625fd3 Made sure everything went to their appropriate devices Brandon Rozek 2019-02-03 00:45:14 -05:00
• 39643f04e1 Simplified in place guassian code Brandon Rozek 2019-02-03 00:31:35 -05:00
• a03abe2bb1 Initial Commit Brandon Rozek 2019-01-31 23:34:32 -05:00