ml-agents

作者	SHA1	备注	提交日期
yanchaosun	1b86b3ae	initialize	5 年前
yanchaosun	3ef4196e	Added the algorithm named ppo_transfer	5 年前
yanchaosun	c2d6f5c0	basic implementation	5 年前
yanchaosun	a9c788d7	new model	5 年前
yanchaosun	ac4c80c2	integrate the implementation and hyperparameters	5 年前
yanchaosun	1e52ad3d	ready for cloud training	5 年前
yanchaosun	05a96355	remove slim package	5 年前
yanchaosun	ad95032b	transfer path	5 年前
yanchaosun	59251abe	change yamls	5 年前
yanchaosun	a80915a8	yaml update	5 年前
yanchaosun	666c8ba9	new cloud training change	5 年前
yanchaosun	59e93b0b	transfer config	5 年前
yanchaosun	d7402406	multiple sizes configs	5 年前
yanchaosun	5eccb4c9	new transfer test for cloud	5 年前
yanchaosun	d1e8d344	with swish activation	5 年前
yanchaosun	f74af710	fix problem	5 年前
yanchaosun	3f0cc587	fix	5 年前
yanchaosun	4ba543e5	fix bug	5 年前
GitHub	839eb2cb	Develop model transfer test (#4214 ) * test env, and code integration * delete results	5 年前
yanchaosun	7e3216ae	simple env test	5 年前
yanchaosun	cdaaa318	bisim	5 年前
yanchaosun	3d0d359c	bisimulation draft	5 年前
yanchaosun	1fdbfe65	no normalization	5 年前
yanchaosun	5a778ca3	fix normalization	5 年前
yanchaosun	a212fef9	new bisim implementation	5 年前
yanchaosun	aca8cd58	update with new alternating	5 年前
yanchaosun	0e2f6e19	small fix	5 年前
yanchaosun	ec929746	minor update	5 年前
Andrew Cohen	d0133066	working	5 年前
yanchaosun	9bc90956	fix bug with bisimulation	5 年前
yanchaosun	f8b91faa	try to fix the bisim metric	5 年前
yanchaosun	ce36349b	some changes	5 年前
Andrew Cohen	1b17ae56	add tanh activ	5 年前
Andrew Cohen	5fa28f5f	merge YC changes	5 年前
yanchaosun	28355444	bisim fix, disable stop gradient	5 年前
yanchaosun	3246570c	added action encoder, and flags related with action training/transferring; set model_schedule as a changable hyperparameter	5 年前
yanchaosun	b991096b	update target encoder soft copy	5 年前
yanchaosun	b74294bf	target encoders and new forward loss	5 年前
yanchaosun	0c468084	sac transfer implementation; disable action encoder	5 年前
yanchaosun	36f36750	target critic for ppo	5 年前
yanchaosun	6df774ed	update: separate model train as an option	5 年前
yanchaosun	e8fcc4bb	ppo new implementation	5 年前
Andrew Cohen	72bf7b72	reward loss separate	5 年前
yanchaosun	b5e02978	sac crawler config	5 年前
yanchaosun	2e927257	separate policy net	4 年前

45 次代码提交 (d94b81c0-e0f4-45b1-99b3-9a9f24f31b4c)