yanchaosun
|
c2d6f5c0
|
basic implementation
|
5 年前 |
|
yanchaosun
|
a9c788d7
|
new model
|
4 年前 |
|
yanchaosun
|
ac4c80c2
|
integrate the implementation and hyperparameters
|
4 年前 |
|
yanchaosun
|
f0881a94
|
fix commands for cloud training
|
4 年前 |
|
yanchaosun
|
05a96355
|
remove slim package
|
4 年前 |
|
yanchaosun
|
ad95032b
|
transfer path
|
4 年前 |
|
yanchaosun
|
a80915a8
|
yaml update
|
4 年前 |
|
yanchaosun
|
666c8ba9
|
new cloud training change
|
4 年前 |
|
yanchaosun
|
5eccb4c9
|
new transfer test for cloud
|
4 年前 |
|
yanchaosun
|
858b97ec
|
bug fix
|
4 年前 |
|
yanchaosun
|
da87eae9
|
predict model fix
|
4 年前 |
|
yanchaosun
|
d1e8d344
|
with swish activation
|
4 年前 |
GitHub
|
839eb2cb
|
Develop model transfer test (#4214)
* test env, and code integration
* delete results
|
4 年前 |
|
yanchaosun
|
7e3216ae
|
simple env test
|
4 年前 |
|
yanchaosun
|
cdaaa318
|
bisim
|
4 年前 |
|
yanchaosun
|
3d0d359c
|
bisimulation draft
|
4 年前 |
|
yanchaosun
|
1fdbfe65
|
no normalization
|
4 年前 |
|
yanchaosun
|
5a778ca3
|
fix normalization
|
4 年前 |
|
yanchaosun
|
a212fef9
|
new bisim implementation
|
4 年前 |
|
yanchaosun
|
0e2f6e19
|
small fix
|
4 年前 |
|
yanchaosun
|
ec929746
|
minor update
|
4 年前 |
Andrew Cohen
|
d0133066
|
working
|
4 年前 |
|
yanchaosun
|
9bc90956
|
fix bug with bisimulation
|
4 年前 |
|
Andrew Cohen
|
b6bf1860
|
fix bisim metric
|
4 年前 |
|
yanchaosun
|
f8b91faa
|
try to fix the bisim metric
|
4 年前 |
|
yanchaosun
|
ce36349b
|
some changes
|
4 年前 |
|
Andrew Cohen
|
1b17ae56
|
add tanh activ
|
4 年前 |
|
yanchaosun
|
7508a130
|
small fix
|
4 年前 |
|
yanchaosun
|
caeffa3e
|
add two envs
|
4 年前 |
|
Andrew Cohen
|
5fa28f5f
|
merge YC changes
|
4 年前 |
|
yanchaosun
|
28355444
|
bisim fix, disable stop gradient
|
4 年前 |
|
yanchaosun
|
3246570c
|
added action encoder, and flags related with action training/transferring; set model_schedule as a changable hyperparameter
|
4 年前 |
|
yanchaosun
|
80bad241
|
init sac transfer, and added action encoder to bisim; configs for crawler
|
4 年前 |
|
yanchaosun
|
a505cb16
|
new config
|
4 年前 |
|
yanchaosun
|
b991096b
|
update target encoder soft copy
|
4 年前 |
|
Andrew Cohen
|
0c7db26a
|
target encoder
|
4 年前 |
|
yanchaosun
|
b74294bf
|
target encoders and new forward loss
|
4 年前 |
|
yanchaosun
|
0c468084
|
sac transfer implementation; disable action encoder
|
4 年前 |
|
yanchaosun
|
0a1a30d3
|
sac update
|
4 年前 |
|
yanchaosun
|
00bb821c
|
fix sac transfer problems
|
4 年前 |
|
Andrew Cohen
|
302e8e77
|
no action encoder
|
4 年前 |
|
yanchaosun
|
2b67d1a6
|
fix crawler config
|
4 年前 |
|
Andrew Cohen
|
9c012d6a
|
no op buffer no acen
|
4 年前 |
|
Andrew Cohen
|
2dec257c
|
no encoder for single task
|
4 年前 |
|
yanchaosun
|
6df774ed
|
update: separate model train as an option
|
4 年前 |
|
Andrew Cohen
|
2cd0de04
|
action enc
|
4 年前 |
|
yanchaosun
|
3ce88589
|
1 layer everything
|
4 年前 |
|
Andrew Cohen
|
463db9e8
|
backprop enc single task
|
4 年前 |
|
Andrew Cohen
|
12eda929
|
try reload all
|
4 年前 |
|
yanchaosun
|
3762358d
|
fix action stop gradient
|
4 年前 |
|
yanchaosun
|
3ed56471
|
remove bi-forward-loss
|
4 年前 |
|
yanchaosun
|
c5d9e376
|
add bi-forward-loss back
|
4 年前 |
|
yanchaosun
|
2e927257
|
separate policy net
|
4 年前 |
|
yanchaosun
|
1ce53c55
|
discrete action
|
4 年前 |
