17 Commits

Author	SHA1	Message	Date
mhz	91d4e3c7ad	try to get the original perf	2024-09-16 22:45:12 +02:00
mhz	c867aef5a6	now we add reward wait to test	2024-09-15 22:21:09 +02:00
mhz	1ad520d248	can run but need to test whtich pth is	2024-09-15 22:18:56 +02:00
mhz	94fe13756f	try to update reward func	2024-09-14 23:56:36 +02:00
mhz	2ac17caa3c	need to update the model	2024-09-12 23:40:42 +02:00
mhz	0c60171c71	need to update the model	2024-09-10 16:57:42 +02:00
mhz	97fbdf91c7	try to deploy PPO policy	2024-09-09 23:50:10 +02:00
mhz	5dccf590e7	add sample phase and try to get log prob	2024-09-08 23:26:49 +02:00
mhz	0c4b597dd2	train phase done	2024-09-08 21:09:41 +02:00
mhz	11d9697e06	write some codes for integrate reward code	2024-09-08 20:28:14 +02:00
mhz	73324083ce	update the gpu id	2024-07-03 15:25:46 +02:00
mhz	ba008ae54c	update the main function	2024-07-01 10:02:51 +02:00
mhz	14186fa97f	write test code	2024-06-26 23:41:37 +02:00
mhz	062a27b83f	try update the api in DataInfo	2024-06-26 22:10:07 +02:00
mhz	82299e5213	try to run the graph, commented sampling codes	2024-06-25 00:09:27 +02:00
Hanzhang Ma	4f8945ca07	add somecomments	2024-06-08 21:35:35 +02:00
gang liu	2c00828630	update_name	2024-05-25 15:32:36 -04:00