ecae092534
随机训练匹配llm_action
2024-08-27 10:20:32 +08:00
012e4e0fd4
8.22
2024-08-22 10:06:26 +08:00
94f447c711
meeting
2024-07-30 14:11:23 +08:00
7c186de43d
meeting
2024-07-30 13:31:13 +08:00
16eccf95b6
meeting
2024-07-30 11:33:07 +08:00
9056fbdc79
meeting
2024-07-30 10:38:39 +08:00
23c1ad592d
meeting
2024-07-30 09:05:32 +08:00
993e062068
update environment and agents for improved performance
...
refactors the code for the environment and agent modules to optimize performance and readability.
- Standardizing the order of arguments in solar step function calls.
- Introducing a percentage-based action voltage adjustment in the module
step function to enhance control flexibility.
- Updating PPO and related files to use Generalized Advantage Estimation
(GAE) by default, improving reward shaping and stability.
2024-07-09 10:49:26 +08:00
741fba6cd5
update logic
2024-07-05 15:39:57 +08:00
f26024c8d4
train
2024-06-26 15:44:30 +08:00
f66de9fb54
nothing
2024-06-25 15:08:50 +08:00
9d0b220b54
plot
2024-06-25 14:07:04 +08:00
d7feebab50
llm
2024-06-25 11:02:53 +08:00
2c672d9569
llm
2024-06-25 09:11:30 +08:00
21be0966dc
nothing
2024-06-20 09:19:22 +08:00
b5a1842147
nothing
2024-06-20 09:00:38 +08:00
63f145467b
nothing
2024-06-19 16:01:00 +08:00
53d3ac9ca8
edit the layer normalization
2024-06-19 14:36:11 +08:00
25a5da0e00
test
2024-06-18 14:54:23 +08:00
488a893354
test
2024-06-18 11:24:43 +08:00
5fd1ac5e14
'init'
2024-06-18 10:49:43 +08:00
chenxiaodong