wassname/pytorch-soft-actor-critic
1
0
Fork 0
mirror of https://github.com/wassname/pytorch-soft-actor-critic.git synced 2026-06-27 15:16:26 +08:00
Code Issues Packages Projects Releases Wiki Activity
181 Commits 2 Branches 0 Tags
master
Commit Graph

181 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
wassname f28ca774ed smaller camera, detach critic inputs 2021-01-17 18:27:36 +08:00
wassname 16ca1a351b misc 2021-01-17 13:35:48 +08:00
wassname 9ffe9fa9a2 tidy 2021-01-17 11:53:18 +08:00
wassname e4fd67f3b5 progbar 2021-01-17 11:29:35 +08:00
wassname 5534d4b078 prcoess_obs works, with training by both obs and critic 2021-01-16 18:15:13 +08:00
wassname 093876e414 process obs part1 2021-01-16 16:41:40 +08:00
wassname 0805bfa98f logging 2021-01-16 16:41:14 +08:00
wassname 90d207ca9b logging 2021-01-16 16:40:53 +08:00
wassname cc6e0f2035 misc 2021-01-16 08:35:11 +08:00
wassname 0a71ce15c7 logging 2021-01-10 12:34:34 +08:00
wassname a2c113d754 misc 2021-01-09 20:22:39 +08:00
wassname 4248a88ea4 tune tau etc 2021-01-03 14:54:23 +08:00
wassname 59b845a8a1 play and gitignore 2021-01-03 13:06:01 +08:00
wassname 617ff797ba apple gym runs 2020-12-29 08:53:19 +08:00
wassname 10c6b6e595 load demonstrations use apple_gym 2020-12-29 07:58:53 +08:00
pranz24 1bd1158116 Fix inconsistent seeding & clean up code 2020-07-11 14:15:04 +05:30
pranz24 ec004304a9 I have no idea what I'm doing. 2020-06-06 22:56:10 +05:30
pranz24 e5c349f0b0 tensorboard cleanup 2020-06-06 09:34:03 +05:30
pranz24 dbbbacc39d remove tensorboardX 2020-06-06 08:57:18 +05:30
pranz24 1a3f379b79 small cleanup 2020-06-06 00:38:20 +05:30
pranz24 a1e8d7319e fix for pytorch-1.5 & cleanup 2020-06-06 00:20:05 +05:30
pranz24 e961172767 fix for pytorch-1.5 2020-06-06 00:19:15 +05:30
Pranjal Tandon 847edf58a5 Merge pull request #28 from ihexx/patch-1 
Update main.py
 2020-04-02 05:58:25 +05:30
Gershom b298849694 Update main.py 2020-04-01 01:39:10 -07:00
Pranjal Tandon a45ed97761 Update README.md 2020-02-03 14:31:51 +05:30
Pranjal Tandon d25a856304 Update README.md 2020-02-03 14:25:16 +05:30
Pranjal Tandon 1b0087277d Update sac.py 2020-02-03 14:16:34 +05:30
Pranjal Tandon f1294bb974 Update README.md 2020-02-03 14:16:05 +05:30
Pranjal Tandon 269478d41d Update README.md 2020-02-03 14:11:57 +05:30
Pranjal Tandon 15f725e61c Update sac.py 2020-02-03 14:10:57 +05:30
Pranjal Tandon e687d35243 Update README.md 2020-02-03 14:08:50 +05:30
Pranjal Tandon 0da86b413f Update sac.py 2020-02-03 14:04:15 +05:30
Pranjal Tandon 589b56b264 Update sac.py 2020-02-03 14:00:34 +05:30
Pranjal Tandon 5189f44caa Update README.md 2020-02-03 13:55:23 +05:30
Pranjal Tandon 42d2ff08cb Update sac.py 2020-02-03 13:48:45 +05:30
Pranjal Tandon 73064f31ea Update main.py 2020-02-03 13:46:39 +05:30
Pranjal Tandon d8ba7370e5 Merge pull request #21 from Shmuma/patch-1 
Fix error with DeterministicPolicy
 2019-11-27 13:30:57 +05:30
Max Lapan 3664ba4e60 Fix error with DeterministicPolicy 
More pytorch-native way would be to use `Module.register_buffer()` method. In that case, buffer won't be used in parameters(), but will be converted to CUDA and CPU with `to()` call transparently.
 2019-11-24 18:00:57 +03:00
Pranjal Tandon cc42a1f31c Merge pull request #19 from fgolemo/patch-1 
Update README.md
 2019-09-30 08:05:36 +00:00
Florian Golemo b86fabc23c Update README.md 
typo
 2019-09-29 20:10:11 -04:00
pranz24 5663db7e22 Edit README.md & main.py 2019-09-16 16:42:30 +05:30
pranz24 a1fe838d64 Edit README.md & main.py 2019-09-16 16:40:12 +05:30
pranz24 92486c2498 Edit README.md & main.py 2019-09-16 16:34:56 +05:30
pranz24 6e49320c8c Edit README.md & main.py 2019-09-16 16:31:31 +05:30
pranz24 c2d50837db small fix 2019-09-10 22:29:35 +05:30
Pranjal Tandon 6b6f64db37 Merge pull request #15 from ku2482/master 
Fix bugs of action re-scaling
 2019-08-05 15:25:34 +05:30
Toshiki Watanabe d4cce3869e fix bugs 2019-07-23 11:59:59 +09:00
Toshiki Watanabe d3a6ffda45 Merge branch 'master' of https://github.com/pranz24/pytorch-soft-actor-critic 2019-07-23 11:31:56 +09:00
Toshiki Watanabe ab2c461af0 fix bugs of action rescaling 2019-07-23 11:30:36 +09:00
Pranjal Tandon a40fe29ac6 Merge pull request #13 from ku2482/fix_normalized_actions 
Fix normalized actions
 2019-06-27 15:07:38 +05:30