107 Commits

Author SHA1 Message Date
NM512
bc7bd6f704 erased unnecessary packages import 2023-06-18 17:29:23 +09:00
NM512
2f6ccc5ed1 modified config for MemoryMaze 2023-06-18 17:19:03 +09:00
NM512
b408067d9a avoid DeprecationWarning 2023-06-18 17:18:24 +09:00
NM512
e3329b35e5 applied formatter 2023-06-18 16:57:05 +09:00
NM512
775eb94e7f
Merge pull request #21 from zdx3578/memmaze
Mem maze env
2023-06-18 16:27:49 +09:00
NM512
2a8b2e84e0
Merge branch 'main' into memmaze 2023-06-18 16:27:05 +09:00
zdx
8e005afde5 mem maze env ok 1.2 2023-06-18 09:16:32 +08:00
zdx
152415f32e mem maze env ok 1.1 2023-06-17 23:59:05 +08:00
张德祥
ea446adaf4 mem maze env ok 1 2023-06-17 23:29:53 +08:00
NM512
5dce8cf13b added benchmark task Crafter 2023-06-18 00:02:22 +09:00
NM512
9c58ab62c0 introduced return used in author's code 2023-06-17 16:59:40 +09:00
NM512
784a69f80c set "envs" according to the paper 2023-06-17 15:37:34 +09:00
NM512
ccc98d46c9 applied weight_init for linear layer in Decoder 2023-06-17 15:32:27 +09:00
NM512
970d1dc3e9 bug fix of limits for trunc_normal_ 2023-06-17 15:28:26 +09:00
NM512
f7c505579c erased unnecessary lines 2023-06-17 15:27:09 +09:00
张德祥
1cf0149c10 env v0.13 2023-06-14 20:22:17 +08:00
张德祥
b9120a7440 env v0.12 2023-06-13 21:39:04 +08:00
张德祥
5038a91aad env v0.11 2023-06-13 10:44:54 +08:00
张德祥
7879c6cfe7 env v01 2023-06-13 09:58:03 +08:00
NM512
6c861ca7cb
Merge pull request #14 from ktolnos/dev
Fixed a couple of bugs.
2023-06-06 05:34:13 +09:00
ktolnos
b07badeee6 Fixes for Plan2Explore with actions and for windows. 2023-06-05 22:50:12 +03:00
ktolnos
308eeff09a Fixed RSSM trajectory starts initialization. 2023-06-05 22:49:40 +03:00
NM512
0ff2c061fa updated results of DMC vision 2023-06-04 23:49:05 +09:00
NM512
ac8b846505 added results of DMC proprio 2023-05-21 23:12:51 +09:00
NM512
0faa10ff46 expanded the supported image sizes 2023-05-21 22:00:59 +09:00
NM512
02c3d45fcf modification of expl. 2023-05-21 08:17:47 +09:00
NM512
b8ef214efa bug fix for gym==0.19.0 2023-05-18 21:30:08 +09:00
NM512
d3156ecb06 bug fix for atari env 2023-05-17 22:18:10 +09:00
NM512
7e67dc6910 set default precision as 32 2023-05-17 22:16:55 +09:00
NM512
b984e69b6e added state input capability 2023-05-14 23:38:46 +09:00
NM512
3ebb8ad617 updated README 2023-05-05 18:21:19 +09:00
NM512
d692b377ec memory saving at evaluation 2023-05-05 01:32:08 +09:00
NM512
e5e8bcb284 modified a variable name 2023-04-29 07:57:05 +09:00
NM512
0eb66997fb learnable initial state options for RSSM 2023-04-29 07:54:03 +09:00
NM512
1328ff1088 sampling from the replay buffer across episodes 2023-04-29 07:43:02 +09:00
NM512
12cccd8475 addition of "is_first" and "is_terminal" for envs 2023-04-29 07:34:27 +09:00
NM512
3d0e2c8b5a added .vscode to .gitignore 2023-04-29 07:30:34 +09:00
NM512
2a8b44eb0c erased unnecessary code 2023-04-27 07:42:08 +09:00
NM512
432a359bcf put running episode into replay buffer 2023-04-24 06:25:17 +09:00
NM512
6f0e6c6963 applied formatter to envs 2023-04-23 22:52:30 +09:00
NM512
628b856c63 changed the discount head to predict terminal 2023-04-22 09:34:23 +09:00
NM512
16151efb3c
Merge pull request #6 from truncs/main
That is correct.
Thanks for your contribution!
2023-04-22 09:19:44 +09:00
Aditya
52782d31e3 terminal value is along the sequence dim 2023-04-20 19:05:18 -07:00
NM512
1e070a3daf cleaned up envs 2023-04-15 23:16:43 +09:00
NM512
fba87a33e0 applied formatter to tools 2023-04-15 15:28:09 +09:00
NM512
55ed69bdf7 fix bug when using envs > 1 2023-04-15 15:25:25 +09:00
NM512
cd935b7dd9 set default replay buffer size as 1M 2023-04-05 21:38:51 +09:00
NM512
57ac1c11d3 replaced all tf function to torch 2023-04-03 08:06:34 +09:00
NM512
8bd69bfcd4 bug fix when using multiple environments 2023-04-03 08:00:16 +09:00
NM512
942eae10a9 updated result, requirements and torch version 2023-03-24 07:51:57 +09:00