ml-agents

作者	SHA1	备注	提交日期
Ruo-Ping Dong	6feec58a	add Saver class (only TF working)	4 年前
Ruo-Ping Dong	6d67f857	move tf and add torch model serialization	4 年前
Ruo-Ping Dong	bdb2ba93	small improvements	4 年前
Ruo-Ping Dong	1e15157c	remove print	4 年前
Ruo-Ping Dong	4e87b422	move checkpoint_path logic to saver	4 年前
Ruo-Ping Dong	71fe4df6	fix formatting and test	4 年前
Ruo-Ping Dong	b4713baa	small improvements	4 年前
Ruo-Ping Dong	95858e25	update saver interface and add tests	4 年前
Ruo-Ping Dong	f40996e2	fix export input names	4 年前
Ruo-Ping Dong	1f7b57e0	change brain_name to behavior_name	4 年前
Ruo-Ping Dong	c47ffc20	Rename saver	4 年前
Ruo-Ping Dong	27fb4270	brain_name to behavior_name	4 年前
Ruo-Ping Dong	f5dee9d1	jit for continuous control	4 年前
GitHub	6f534366	Add torch_utils class, auto-detect CUDA availability (#4403 ) * Add torch_utils * Use torch from torch_utils * Add torch to banned modules in CI * Better import error handling * Fix flake8 errors * Address comments * Move networks to GPU if enabled * Switch to torch_utils * More flake8 problems * Move reward providers to GPU/CPU * Remove anothere set default tensor * Fix banned import in test	4 年前
Ervin Teng	3475c686	Temporarily disable exporting	4 年前
Ervin Teng	bed4bf36	Load individual elements if state dict load fails (#5213 ) Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com> Co-authored-by: Ervin T. <ervin@unity3d.com> (cherry picked from commit ac4f43cf18b98d0fc7063b9b831e07429f7ea39e)	3 年前
Andrew Cohen	d6802cf1	load individual elements if state dict load fails	3 年前
Andrew Cohen	a7c6fc3e	clean up exception catching	3 年前
Andrew Cohen	583001c1	use debug statements	3 年前
Andrew Cohen	1283e055	use load_state_dict strict = False	3 年前
Andrew Cohen	31db7aa0	add unexpected keys	3 年前
Andrew Cohen	32f68206	fix typo in warning for unexpected keys	3 年前
Andrew Cohen	1fb2fa73	add debug with error print out	3 年前
Andrew Cohen	2a5b58dd	add special case for non nn.Module load and comment	3 年前
GitHub	5108ec97	Update ml-agents/mlagents/trainers/model_saver/torch_model_saver.py Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>	3 年前
GitHub	14b09ba3	Update ml-agents/mlagents/trainers/model_saver/torch_model_saver.py Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>	3 年前
GitHub	1fbbd97b	Add more verbose messages when using --initialize-from and --resume (#5231 ) * Add more verbose messages when using --initialize-from and resume * Fix typo * Add periods	3 年前
GitHub	28eb43dd	[bug-fix] Delete .pt checkpoints past keep-checkpoints (#5271 ) * Manage non-ONNX files with checkpoint manager too * Update tests * Update training status version * Change ticking of status file version	3 年前

28 次代码提交 (9dfe6c7f-b5c5-488c-8d4f-3c39d9149013)