Naoki Morihira
6ef8646d80
Merge pull request #81 from Ruicky8/patch-1
...
Fix missing advantage computation when reward_EMA is disabled
2026-03-08 13:31:20 +09:00
Unai Ruiz
a8456e95bc
Fix missing advantage computation when reward_EMA is disabled
...
This PR fixes an issue where reward_EMA=False caused adv to be undefined in _compute_actor_loss.
Previously, adv was only computed inside the reward_EMA branch, which resulted in a runtime error when the option was disabled.
2026-03-03 16:34:52 +01:00
NM512
6253f988fe
add deprecation notice and troubleshooting to README
2026-02-21 21:12:39 +09:00
NM512
be5e5ecf40
apply mean to log items for consistency
2026-02-21 20:58:43 +09:00
NM512
7433d1e877
avoid ".to(device)"
2024-09-28 07:58:15 +09:00
NM512
669b7e1b43
fixed observation space for minecraft
2024-09-26 23:05:30 +09:00
NM512
4538f366e7
updated requirements
2024-09-24 00:33:02 +09:00
NM512
6d08232ad7
updated atari100k result
2024-09-24 00:18:47 +09:00
NM512
59939222d1
clean code
2024-09-24 00:16:12 +09:00
NM512
4e50f302cd
updated results
2024-03-11 06:22:09 +09:00
NM512
2cfcaefea2
avoid mutable default argument
2024-03-11 06:21:35 +09:00
NM512
2c7a81a0e2
modified default size for encoder and decoder
2024-01-14 21:59:35 +09:00
NM512
a4fdfad938
bug fix for onehot distribution
2024-01-14 21:55:34 +09:00
NM512
5abaf056ad
fixed mujoco version
2024-01-08 23:52:40 +09:00
NM512
7f66ed5333
erased unused options
2024-01-05 23:23:09 +09:00
NM512
a27711ab96
limit action values in sampling stage
2024-01-05 11:42:45 +09:00
NM512
a9e85e8b7c
modified weight initialization
2024-01-05 10:46:54 +09:00
NM512
4fe9b29ebe
env seed vary between envs of parallel
2024-01-05 10:44:20 +09:00
NM512
78e86703f4
modified loss calculation
2024-01-05 10:44:04 +09:00
NM512
e0487f8206
merged action head into MLP and modified configs
2024-01-05 10:26:48 +09:00
NM512
e0f2017e28
unified the place to initialize the latents
2024-01-05 10:09:13 +09:00
NM512
49d12baa48
added the results of dmc
2023-11-04 10:10:20 +09:00
NM512
0eec12bd1c
added Docker instruction
2023-10-02 07:37:08 +09:00
NM512
1002d8b115
avoid cyclic reference
2023-10-02 07:27:26 +09:00
NM512
f35480f2a6
policy is not given logs
2023-10-01 06:25:23 +09:00
NM512
37da2d3498
Merge branch 'main' of github.com:NM512/dreamerv3-torch into main
2023-09-27 09:19:40 +09:00
NM512
d3576c5a98
added save and load for optimizers
2023-09-27 09:15:37 +09:00
NM512
16635df3e4
removed scheduling function
2023-09-26 20:58:55 +09:00
NM512
1442ee82ed
Merge pull request #36 from WeberSamuel/main
...
Fix Plan2Explore
2023-08-22 22:08:28 +09:00
WeberSamuel
6bf120237b
Fix Plan2Explore
2023-08-19 09:42:54 +02:00
NM512
2cdba230d8
added Dockerfile
2023-08-18 01:40:10 +09:00
NM512
7607a92d71
modified the memorymaze environment
2023-08-16 21:54:09 +09:00
NM512
606ec8af8c
added the option for a deterministic run
2023-08-16 21:46:06 +09:00
NM512
68096d1f62
added log for inventory items in minecraft
2023-08-16 15:52:33 +09:00
NM512
99dc4e4ed1
added crafter result
2023-08-15 20:11:15 +09:00
NM512
9d8483a02f
save snapshots of minecraft
2023-08-06 18:56:02 +09:00
NM512
02cf57b617
added option to parallize
2023-08-05 22:42:03 +09:00
NM512
8571cf656a
modifications for minecraft
2023-08-05 21:13:57 +09:00
NM512
8c471e12d6
erased unnecessary lines of code
2023-08-05 21:11:34 +09:00
NM512
eb14e2488b
modified envs
2023-08-05 21:10:16 +09:00
NM512
a6ad132198
modified wrappers
2023-08-05 21:08:01 +09:00
NM512
3f6659d365
changed treatment of obs shape in minecraft
2023-08-03 08:12:44 +09:00
NM512
d94a719421
bug fix when using normal_1
2023-07-27 10:01:40 +09:00
NM512
6924abdd3e
eval is executed after steps in config elapsed
2023-07-26 01:00:03 +09:00
NM512
43e1b2ab88
fix bug when resetting envs at different time
2023-07-24 22:26:21 +09:00
NM512
22e9f8de7b
set model size L for minecraft in config
2023-07-24 21:42:04 +09:00
NM512
9b97035310
updated README
2023-07-23 22:40:32 +09:00
NM512
394033692c
added minecraft env to README
2023-07-23 22:39:15 +09:00
NM512
12ed21e06d
applied formatter
2023-07-23 22:02:06 +09:00
NM512
afa5ab988d
introduced parallel processing for envs
2023-07-23 21:58:46 +09:00
