yanchaosun
|
f1346bdf
|
multiple seeds
|
4 年前 |
|
yanchaosun
|
6220f7c7
|
linear model
|
4 年前 |
|
yanchaosun
|
86da272d
|
load pv
|
4 年前 |
|
yanchaosun
|
3ce88589
|
1 layer everything
|
4 年前 |
|
yanchaosun
|
2d1ffac5
|
ppo ball
|
4 年前 |
|
yanchaosun
|
f78940c1
|
less features
|
4 年前 |
|
yanchaosun
|
120d1c3a
|
cloud config: non-linear policy
|
4 年前 |
|
yanchaosun
|
66bbdae9
|
sac crawler configs
|
4 年前 |
|
yanchaosun
|
b40bd941
|
new 3dball rewards
|
4 年前 |
|
yanchaosun
|
e8fcc4bb
|
ppo new implementation
|
4 年前 |
|
yanchaosun
|
42c9ba43
|
reuse encoder and linear
|
4 年前 |
|
yanchaosun
|
57d3ba64
|
change path
|
4 年前 |
|
yanchaosun
|
44312bdb
|
linear policy and linear forward
|
4 年前 |
|
yanchaosun
|
8c03c82a
|
use target
|
4 年前 |
|
yanchaosun
|
c48b6429
|
numpy fix, config 3dball
|
4 年前 |
|
yanchaosun
|
aa0e896f
|
linear value, no target
|
4 年前 |
|
yanchaosun
|
6df774ed
|
update: separate model train as an option
|
4 年前 |
|
yanchaosun
|
36f36750
|
target critic for ppo
|
4 年前 |
|
yanchaosun
|
f937aa96
|
3dball ppo: without var predict
|
4 年前 |
|
yanchaosun
|
d706f28c
|
use off policy buffer to transfer
|
4 年前 |
|
yanchaosun
|
f55fd920
|
remove transfer from yaml
|
4 年前 |
|
yanchaosun
|
910707dd
|
PPO 3dball config
|
4 年前 |
|
yanchaosun
|
d1f57dec
|
separate value net config
|
4 年前 |
|
yanchaosun
|
42c0c333
|
fig bug
|
4 年前 |
|
yanchaosun
|
2b67d1a6
|
fix crawler config
|
4 年前 |
|
yanchaosun
|
cc9a38ae
|
cloud config with shared encoder
|
4 年前 |
GitHub
|
42d61c09
|
Crawler fix (#4270)
* fixed crawler issue
* fixed crawler again
|
4 年前 |
|
yanchaosun
|
e2f0b3ca
|
fix transfer
|
4 年前 |
|
yanchaosun
|
00bb821c
|
fix sac transfer problems
|
4 年前 |
|
yanchaosun
|
a9c6105d
|
configs
|
4 年前 |
|
yanchaosun
|
7226256d
|
config: no alter
|
4 年前 |
|
yanchaosun
|
0a1a30d3
|
sac update
|
4 年前 |
|
yanchaosun
|
0c468084
|
sac transfer implementation; disable action encoder
|
4 年前 |
|
yanchaosun
|
b74294bf
|
target encoders and new forward loss
|
4 年前 |
|
yanchaosun
|
6657129c
|
config: not reuse encoder
|
5 年前 |
|
yanchaosun
|
b991096b
|
update target encoder soft copy
|
5 年前 |
|
yanchaosun
|
62284176
|
change id
|
5 年前 |
|
yanchaosun
|
c1bccaf5
|
diable bisim
|
5 年前 |
|
yanchaosun
|
9a19f6e5
|
disable bisim
|
5 年前 |
|
yanchaosun
|
a505cb16
|
new config
|
5 年前 |
|
yanchaosun
|
f81feec4
|
config fix; basic sac
|
5 年前 |
|
yanchaosun
|
80bad241
|
init sac transfer, and added action encoder to bisim; configs for crawler
|
5 年前 |
|
yanchaosun
|
696ec0cc
|
new plots
|
5 年前 |
|
yanchaosun
|
fb5c33c1
|
test code
|
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
|
8fc18e5d
|
plotting
|
5 年前 |
