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 |
|
NM512
|
2504426164
|
updated results
|
2023-03-20 21:00:01 +09:00 |
|
NM512
|
5ad0f6e9ca
|
clear eval episodes for saving memory
|
2023-03-20 20:55:06 +09:00 |
|
NM512
|
44f8edc115
|
updated results
|
2023-03-18 19:07:12 +09:00 |
|
NM512
|
6273444394
|
modified based on author's implementation
|
2023-03-18 08:38:23 +09:00 |
|
NM512
|
a678a509b9
|
updated results
|
2023-02-18 14:42:22 +09:00 |
|
NM512
|
f96ad071d1
|
modified network structures to match the paper
|
2023-02-18 10:13:02 +09:00 |
|
NM512
|
fb5c21557a
|
Initial Commit
|
2023-02-12 22:35:25 +09:00 |
|