Commit Graph
24047 Commits
Author SHA1 Message Date
nishantkr18 b6476e8a77 Added test for multi-action support for sac 2020-08-18 13:28:50 +05:30
nishantkr18 602cdd5df6 Added support for multiple actions in action space for sac 2020-08-17 13:23:55 +05:30
favre49 da83453e24 Merge pull request #2487 from nishantkr18/sac
Addition of Soft Actor-Critic to RL methods
2020-08-12 23:17:49 +05:30
nishantkr18 f19e3ce130 increased avg reward threshold for test 2020-08-12 08:59:21 +05:30
Mikhail Lozhnikov 99d11a9b4d Merge remote-tracking branch 'mrityunjay-tripathi/FixLinearLayer' (PR #2404) 2020-08-11 16:20:36 +03:00
nishantkr18 353d8ac734 Doc and style fixes 2020-08-11 09:30:41 +05:30
nishantkr18 1307926946 added citation to paper and other doc changes 2020-08-08 23:24:01 +05:30
Ryan Birmingham 0ed562bd52 Merge pull request #2529 from jeffin143/preprocess-test
Migrate preprocess_* and related test from boost to catch2
2020-08-08 08:28:24 -04:00
nishantkr18 8599531acd bug fix in matrix manupilation in categorical 2020-08-08 15:47:52 +05:30
nishantkr18 fb4dbe2886 Updated HISTORY 2020-08-08 11:52:18 +05:30
nishantkr18 902a7f2a88 Added rho as a training parameter for soft actor critic 2020-08-08 11:50:51 +05:30
nishantkr18 3fdf66d24f merged master and added modifications to state rep of pendulum env 2020-08-08 11:38:46 +05:30
Mrityunjay Tripathi a9465119f5 some style fixes and removing pointer type objects 2020-08-08 09:05:53 +05:30
favre49 42254e3ee9 Merge pull request #2543 from rcurtin/rename-go-util
Rename libgo_util.so to libmlpack_go_util.so.
2020-08-07 07:44:24 +05:30
jeffin samandRyan Curtin dd0882d1fe Apply suggestions from code review
Co-authored-by: Ryan Curtin <ryan@ratml.org>
2020-08-07 02:52:02 +05:30
Mrityunjay Tripathi be8caec05d adapt to catch test 2020-08-06 23:51:50 +05:30
Mrityunjay Tripathi d75c104f2d Merge branch 'master' of https://github.com/mlpack/mlpack into FixLinearLayer 2020-08-06 22:11:01 +05:30
Marcus Edel 2d25990246 Merge pull request #2454 from nishantkr18/categorical
Addition of Categorical DQN.
2020-08-06 13:04:11 +02:00
Mrityunjay Tripathi f15174657a Merge branch 'master' of https://github.com/mlpack/mlpack into FixLinearLayer 2020-08-06 13:39:12 +05:30
nishantkr18 1166d471dd style fixes 2020-08-06 10:00:05 +05:30
Ryan Curtin c3d5e1633f Merge remote-tracking branch 'origin/master' into rename-go-util 2020-08-05 18:41:13 -04:00
Ryan Curtin 0e87eb6c16 Fix cgo LDFLAGS. 2020-08-05 18:40:57 -04:00
Nishant Kumarandfavre49 f089e49766 Update src/mlpack/methods/reinforcement_learning/q_networks/categorical_dqn.hpp
Co-authored-by: favre49 <40389657+favre49@users.noreply.github.com>
2020-08-06 00:04:58 +05:30
nishantkr18 5facccf10c reverting to using two q networks as critic 2020-08-05 15:01:29 +05:30
Mikhail Lozhnikov 4ae4dd6ccc Merge remote-tracking branch 'mrityunjay-tripathi/embedding' (PR #2398) 2020-08-05 10:34:41 +03:00
Ryan Birmingham 9e706011bb Merge pull request #2494 from iamshnoo/soft_margin_loss
Soft Margin Loss function
2020-08-05 00:31:50 -04:00
Mrityunjay Tripathi 2418383e69 Merge branch 'master' of https://github.com/mlpack/mlpack into embedding 2020-08-05 00:23:15 +05:30
saksham189 a9d9430f9b Merge pull request #2552 from kartikdutt18/DeterministicFFN
Changes in Deterministic settings of FNN.
2020-08-04 23:55:31 +05:30
nishantkr18 c8e4f08e9c Doc changes and adding categorical parameters to training configs 2020-08-04 23:48:40 +05:30
Mrityunjay Tripathi f146e3e2b3 fix static code analysis error 2020-08-04 22:55:30 +05:30
kartikdutt18 d85c689424 static analysis check fixes 2020-08-04 20:33:35 +05:30
Mrityunjay TripathiandMikhail Lozhnikov 172bd68d35 apply suggestions from code review
Co-authored-by: Mikhail Lozhnikov <lozhnikovma@gmail.com>
2020-08-04 18:46:13 +05:30
kartikdutt18 8ddd2250fe Style fix 2020-08-04 17:24:35 +05:30
kartikdutt18 d570d7c694 Add empty line after tests 2020-08-04 17:14:14 +05:30
kartikdutt18 bdb5abd181 Changes in Deterministic parameter of FNN, default to train mode 2020-08-04 17:11:11 +05:30
Ryan Birmingham a6ca135997 Merge pull request #2545 from jeffin143/decision-test
Migrate decision_* and related test from boost to catch2
2020-08-04 00:01:51 -04:00
Mrityunjay Tripathi c32c47137b correcting catch tests 2020-08-04 00:11:57 +05:30
jeffin sam 163220923f Merge branch 'master' into preprocess-test 2020-08-03 23:39:04 +05:30
Mrityunjay Tripathi f7354abc0b Merge branch 'master' of https://github.com/mlpack/mlpack into embedding 2020-08-03 22:49:29 +05:30
favre49 c62fb588a8 Merge pull request #2551 from jeffin143/ann-test
migrate ann_* and related test from boost to catch2
2020-08-03 22:06:56 +05:30
nishantkr18 4a7c65962d removed acrobot test 2020-08-03 20:25:44 +05:30
Mrityunjay Tripathi 5081d77d6c trigger the build 2020-08-03 17:25:53 +05:30
Mrityunjay Tripathi f3056ff6ed some correction in comments 2020-08-03 13:41:44 +05:30
Mrityunjay Tripathi 345b312c00 add comments about matrix dimensions 2020-08-03 12:24:26 +05:30
Mrityunjay TripathiandMikhail Lozhnikov 0e3458f244 apply suggestions from code review
Co-authored-by: Mikhail Lozhnikov <lozhnikovma@gmail.com>
2020-08-03 10:59:55 +05:30
Mrityunjay Tripathi af2f037fbf Merge branch 'master' of https://github.com/mlpack/mlpack into embedding 2020-08-02 08:46:26 +05:30
Ryan Curtin f6ca446400 Merge branch 'mercierc-feat/bayesian_ridge' into master 2020-08-01 17:03:59 -04:00
Ryan Curtin 977f326251 Update HISTORY. 2020-08-01 17:03:39 -04:00
Ryan Curtin c7f9b48547 Merge branch 'feat/bayesian_ridge' of https://github.com/mercierc/mlpack into mercierc-feat/bayesian_ridge 2020-08-01 17:01:33 -04:00
jeffin143 ff4ef04782 style fixes 2020-08-02 01:48:59 +05:30