Fangshengjun's workspace
Runs
45
Name
2 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
UtilsRL.numpy_fp
UtilsRL.precision
UtilsRL.torch_fp
actor_hidden_dims
actor_update_freq
alpha
auto_alpha
batch_size
clip_max
critic_q_hidden_dims
critic_q_update_freq
critic_v_hidden_dims
critic_v_update_freq
debug
discount
domain
env
env_type
eval_episode
eval_interval
learning_rate
log_interval
loss_temperature
max_buffer_size
max_trajectory_length
name
num_epoch
random_policy_epoch
reward_scale
save_interval
seed
step_per_epoch
target_update_freq
task
tau
wandb.entity
wandb.project
warmup_epoch
Eval/episode_return_mean
Eval/episode_return_std
Eval/length_mean
Eval/length_std
loss/actor_loss
loss/alpha_loss
Finished
gaochenxiao
8s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
quadruped
Quadruped-Run-v1
dmc
10
10
0.0001
10
5
1000000
1000
dmc
2000
5
1
50
3
1000
2
run
0.005
lamda-rl
XSAC-Online
5
902.06293
106.76011
1000
0
-
-
Finished
gaochenxiao
8s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
walker
Walker-Run-v1
dmc
10
10
0.0001
10
2
1000000
1000
dmc
2000
5
1
50
4
1000
2
run
0.005
lamda-rl
XSAC-Online
5
807.85174
9.29318
1000
0
-
-
Finished
gaochenxiao
8s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
hopper
Hopper-Hop-v1
dmc
10
10
0.0001
10
1
1000000
1000
dmc
2000
5
1
50
0
1000
2
hop
0.005
lamda-rl
XSAC-Online
5
354.9666
6.25243
1000
0
-
-
Finished
gaochenxiao
10s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
hopper
Hopper-Hop-v1
dmc
10
10
0.0001
10
1
1000000
1000
dmc
2000
5
1
50
2
1000
2
hop
0.005
lamda-rl
XSAC-Online
5
274.1497
4.93152
1000
0
-
-
Finished
gaochenxiao
9s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
quadruped
Quadruped-Run-v1
dmc
10
10
0.0001
10
5
1000000
1000
dmc
2000
5
1
50
2
1000
2
run
0.005
lamda-rl
XSAC-Online
5
940.79377
27.24105
1000
0
-
-
Finished
gaochenxiao
8s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
walker
Walker-Run-v1
dmc
10
10
0.0001
10
2
1000000
1000
dmc
2000
5
1
50
0
1000
2
run
0.005
lamda-rl
XSAC-Online
5
848.32602
21.53678
1000
0
-
-
Finished
gaochenxiao
8s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
hopper
Hopper-Hop-v1
dmc
10
10
0.0001
10
1
1000000
1000
dmc
2000
5
1
50
3
1000
2
hop
0.005
lamda-rl
XSAC-Online
5
431.66034
6.67548
1000
0
-
-
Finished
gaochenxiao
10s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
quadruped
Quadruped-Run-v1
dmc
10
10
0.0001
10
5
1000000
1000
dmc
2000
5
1
50
1
1000
2
run
0.005
lamda-rl
XSAC-Online
5
913.65682
33.13303
1000
0
-
-
Finished
gaochenxiao
10s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
walker
Walker-Run-v1
dmc
10
10
0.0001
10
2
1000000
1000
dmc
2000
5
1
50
1
1000
2
run
0.005
lamda-rl
XSAC-Online
5
850.98875
7.76743
1000
0
-
-
Finished
gaochenxiao
7s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
quadruped
Quadruped-Run-v1
dmc
10
10
0.0001
10
5
1000000
1000
dmc
2000
5
1
50
0
1000
2
run
0.005
lamda-rl
XSAC-Online
5
944.46921
20.18237
1000
0
-
-
Finished
gaochenxiao
7s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
hopper
Hopper-Hop-v1
dmc
10
10
0.0001
10
1
1000000
1000
dmc
2000
5
1
50
4
1000
2
hop
0.005
lamda-rl
XSAC-Online
5
305.44428
6.99744
1000
0
-
-
Finished
gaochenxiao
15s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
walker
Walker-Run-v1
dmc
10
10
0.0001
10
2
1000000
1000
dmc
2000
5
1
50
2
1000
2
run
0.005
lamda-rl
XSAC-Online
5
826.15448
9.92172
1000
0
-
-
Finished
gaochenxiao
9s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
cheetah
Cheetah-Run-v1
dmc
10
10
0.0001
10
2
1000000
1000
dmc
2000
5
1
50
1
1000
2
run
0.005
lamda-rl
XSAC-Online
5
857.22909
70.99415
1000
0
-
-
Finished
gaochenxiao
9s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
cheetah
Cheetah-Run-v1
dmc
10
10
0.0001
10
2
1000000
1000
dmc
2000
5
1
50
3
1000
2
run
0.005
lamda-rl
XSAC-Online
5
833.00439
233.59349
1000
0
-
-
Finished
gaochenxiao
8s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
hopper
Hopper-Hop-v1
dmc
10
10
0.0001
10
1
1000000
1000
dmc
2000
5
1
50
1
1000
2
hop
0.005
lamda-rl
XSAC-Online
5
0
0
1000
0
-
-
Finished
gaochenxiao
11s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
cheetah
Cheetah-Run-v1
dmc
10
10
0.0001
10
2
1000000
1000
dmc
2000
5
1
50
4
1000
2
run
0.005
lamda-rl
XSAC-Online
5
912.27464
4.70767
1000
0
-
-
Finished
gaochenxiao
8s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
walker
Walker-Run-v1
dmc
10
10
0.0001
10
2
1000000
1000
dmc
2000
5
1
50
3
1000
2
run
0.005
lamda-rl
XSAC-Online
5
805.90187
5.44015
1000
0
-
-
Finished
gaochenxiao
10s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
cheetah
Cheetah-Run-v1
dmc
10
10
0.0001
10
2
1000000
1000
dmc
2000
5
1
50
2
1000
2
run
0.005
lamda-rl
XSAC-Online
5
907.64097
4.45452
1000
0
-
-
Finished
gaochenxiao
8s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
quadruped
Quadruped-Run-v1
dmc
10
10
0.0001
10
5
1000000
1000
dmc
2000
5
1
50
4
1000
2
run
0.005
lamda-rl
XSAC-Online
5
926.77225
39.6005
1000
0
-
-
Finished
gaochenxiao
13s
-
numpy.float32
float32
torch.float32
[1024,1024]
2
0.2
true
1024
10
[1024,1024]
1
[1024,1024]
1
false
0.99
cheetah
Cheetah-Run-v1
dmc
10
10
0.0001
10
2
1000000
1000
dmc
2000
5
1
50
0
1000
2
run
0.005
lamda-rl
XSAC-Online
5
90.5238
44.32822
1000
0
-
-
1-20
of 45