wassname/pyrobolearn
1
0
Fork 0
mirror of https://github.com/wassname/pyrobolearn.git synced 2026-09-20 13:11:01 +08:00
Code Issues Packages Projects Releases Wiki Activity
126 Commits 2 Branches 0 Tags
763fd8d8d4383d0737aea0cd6b854fa33879e483
Commit Graph
126 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Brian Delhaisse 763fd8d8d4 add ecaa9, techpod, flappy, blackbird 2019-05-12 07:16:41 +02:00
Brian Delhaisse 41927eb606 refactor and clean sim, body, robot, and world 2019-05-09 06:27:05 +02:00
Brian Delhaisse f63ccf92f7 add 'add_trajectory' method in storages 2019-05-08 20:01:15 +02:00
Brian Delhaisse 749b98e800 update several classes: add copy/deepcopy methods (ongoing) 2019-05-08 07:43:45 +02:00
Brian Delhaisse 9e68606c9a update simulators: add multiprocessing example with bullet + implement copy/deepcopy 2019-05-08 06:36:30 +02:00
Brian Delhaisse 999466d6eb update bullet simulator: fix render/hide GUI + add history (ongoing) 2019-05-07 07:22:32 +02:00
Brian Delhaisse 849dcfa5b8 update reward processors: account for reward.range 2019-05-07 03:43:28 +02:00
Brian Delhaisse 00a1513fda update rewards: add range that automatically updates based on operations 2019-05-07 03:23:41 +02:00
Brian Delhaisse 91cd04b196 update envs: add actions, reward range, and update render/hide/close 2019-05-06 18:26:13 +02:00
Brian Delhaisse 4d5d8451c5 update simulators and world: get available 3D models + update render() 2019-05-04 04:18:41 +02:00
Brian Delhaisse c237b4dd12 fix urdf color for quadcopter and wam 2019-05-03 18:51:17 +02:00
Brian Delhaisse cf0fec78e5 fix urdf color for pleurobot 2019-05-03 04:53:35 +02:00
Brian Delhaisse df6efe54d9 fix urdf color for pepper 2019-05-03 04:36:23 +02:00
Brian Delhaisse 25a55b2cab add DMP example 2019-05-03 03:58:58 +02:00
Brian Delhaisse a7be1285e8 update and fix few parts (nothing serious) 2019-05-03 03:58:39 +02:00
Brian Delhaisse 49c8c1ffd1 update gp doc 2019-05-02 15:01:38 +02:00
Brian Delhaisse cb3a8b3aae add gplvm 2019-05-02 04:21:41 +02:00
Brian Delhaisse dddc8d7a47 update world: update heightmap and terrain generators 2019-05-01 05:50:54 +02:00
Brian Delhaisse 0033bf0104 update ground reference points in legged robots 2019-05-01 05:50:22 +02:00
Brian Delhaisse 1ff346ffec update/refactor utils 2019-04-29 04:09:43 +02:00
Brian Delhaisse d136069115 correct sensors 2019-04-29 01:35:06 +02:00
Brian Delhaisse 07248b3b02 update legged robots: support polygon + ground ref. points + friction cones 2019-04-28 23:56:25 +02:00
Brian Delhaisse 8eac2c7bea update robots + add shadow hand + units converter 2019-04-28 01:26:49 +02:00
Brian Delhaisse 782175419a update/refactor states: add window and ticks 2019-04-26 04:38:58 +02:00
Brian Delhaisse 95d734db7a fix camera in bridge mousekeyboard 2019-04-26 04:38:34 +02:00
Brian Delhaisse 4a0985da8a add ella (ongoing-part1) 2019-04-26 01:04:12 +02:00
Brian Delhaisse f3b002042c update nn: add mann (part1) 2019-04-24 03:41:07 +02:00
Brian Delhaisse 15241e541f update state: add history window (ongoing) 2019-04-23 01:21:00 +02:00
Brian Delhaisse 002ed26e31 clean/update world and world camera 2019-04-23 01:14:34 +02:00
Brian Delhaisse 2088cd5e57 update utils.data_structures: add queues 2019-04-22 17:21:17 +02:00
Brian Delhaisse 062969be8d add dmpytorch 2019-04-21 22:11:14 +02:00
Brian Delhaisse 17e7b454e1 refactor/update optimizers (ongoing) 2019-04-19 17:43:52 +02:00
Brian Delhaisse 2d53773406 update distributions + fix errors in losses/explorations 2019-04-19 04:42:25 +02:00
Brian Delhaisse 91c61c98e8 add metrics (ongoing), fix minor errors and refactor rl algos 2019-04-19 01:14:53 +02:00
Brian Delhaisse 807d51e4d5 fix few errors and update policy, storage, losses, returns, algos 2019-04-18 14:05:31 +02:00
Brian Delhaisse a55fb6f58a update RL updater 2019-04-18 03:35:27 +02:00
Brian Delhaisse f5abc15008 refactor returns and losses 2019-04-18 03:34:46 +02:00
Brian Delhaisse 4cc9454f15 update dynamic model and loss 2019-04-18 02:31:05 +02:00
Brian Delhaisse 40d95ecde8 correct few errors in policies 2019-04-17 18:05:59 +02:00
Brian Delhaisse 622b834857 refactor RL algos + fix small errors in policy/exploration 2019-04-17 16:46:50 +02:00
Brian Delhaisse e56855ce27 remove openvr import 2019-04-17 16:36:03 +02:00
Brian Delhaisse 01b50afab6 update/refactor parameter updaters 2019-04-17 15:50:42 +02:00
Brian Delhaisse bda3b4a9f0 fix import error with ER 2019-04-17 15:46:45 +02:00
Brian Delhaisse bab65a358d remove baselines import in gym_wrapper 2019-04-17 15:43:08 +02:00
Brian Delhaisse e8e6ef6f8c refactor storages/losses/algos/priorities 2019-04-17 01:43:04 +02:00
Brian Delhaisse f3a49a9f21 correct/update setup.py 2019-04-16 15:08:42 +02:00
Brian Delhaisse 92bea93fde refactor estimators/returns, losses, and storages 2019-04-15 21:40:35 +02:00
Brian Delhaisse fae7c57a86 refactor storages: change observations to states + minor details 2019-04-15 14:35:08 +02:00
Brian Delhaisse 4a391ed77a refactor estimators/returns/targets 2019-04-15 14:28:40 +02:00
Brian Delhaisse 4f8e791dc7 add docs: manipulative and locomotive skills 2019-04-15 11:17:36 +02:00