Gaochenxiao's workspace
Runs
60
Name
15 visualized
task: halfcheetah-medium-replay-v2
task: halfcheetah-medium-replay-v2
5
task: hopper-expert-v2
task: hopper-expert-v2
5
task: hopper-medium-replay-v2
task: hopper-medium-replay-v2
5
task: walker2d-medium-v2
task: walker2d-medium-v2
5
task: halfcheetah-medium-v2
task: halfcheetah-medium-v2
5
task: hopper-medium-expert-v2
task: hopper-medium-expert-v2
5
task: walker2d-medium-replay-v2
task: walker2d-medium-replay-v2
5
task: walker2d-expert-v2
task: walker2d-expert-v2
5
task: halfcheetah-medium-expert-v2
task: halfcheetah-medium-expert-v2
5
task: hopper-medium-v2
task: hopper-medium-v2
5
task: halfcheetah-expert-v2
task: halfcheetah-expert-v2
5
task: walker2d-medium-expert-v2
task: walker2d-medium-expert-v2
5
State
Notes
User
Tags
Created
Runtime
Sweep
UtilsRL.numpy_fp
UtilsRL.precision
UtilsRL.torch_fp
batch_size
debug
discard_last
discount
eval_episode
eval_interval
hidden_dims
learning_rate
log_interval
logstd_hard_clip
max_action
max_epoch
name
normalize_obs
normalize_reward
save_interval
seed
step_per_epoch
task
tau
temperature
wandb.entity
wandb.project
device
Eval/length_mean
Eval/length_std
Eval/normalized_score_mean
Eval/normalized_score_std
loss/actor_loss
loss/behavior_loss
loss/q_loss
loss/v_loss
Finished
-
gaochenxiao
6m 43s
-
numpy.float32
float32
torch.float32
256
false
true
0.99
10
10
256
0.0003
10
false
1
1000
d4rl
false
false
50
2
1000
halfcheetah-medium-replay-v2
0.005
0.5
lamda-rl
InAC-D4RL
["cuda:11","cuda:12","cuda:13","cuda:14","cuda:15"]
1000
0
44.64061
2.20609
3192.02512
1.07092
57.03051
17.92703
Finished
-
gaochenxiao
6m 57s
-
numpy.float32
float32
torch.float32
256
false
true
0.99
10
10
256
0.0003
10
false
1
1000
d4rl
false
false
50
2
1000
hopper-expert-v2
0.005
0.01
lamda-rl
InAC-D4RL
["cuda:11","cuda:12","cuda:13","cuda:14","cuda:15"]
766.48
108.89115
85.89596
12.71212
-2825.3521
-0.43783
0.81496
0.35218
Finished
-
gaochenxiao
5m 42s
-
numpy.float32
float32
torch.float32
256
false
true
0.99
10
10
256
0.0003
10
false
1
1000
d4rl
false
false
50
2
1000
hopper-medium-replay-v2
0.005
0.5
lamda-rl
InAC-D4RL
["cuda:11","cuda:12","cuda:13","cuda:14","cuda:15"]
843.84
46.38378
79.69666
4.38961
706.9862
0.94282
25.68156
10.34167
Finished
-
gaochenxiao
6m 36s
-
numpy.float32
float32
torch.float32
256
false
true
0.99
10
10
256
0.0003
10
false
1
1000
d4rl
false
false
50
2
1000
walker2d-medium-v2
0.005
0.33
lamda-rl
InAC-D4RL
["cuda:11","cuda:12","cuda:13","cuda:14","cuda:15"]
854.06
156.59927
72.88459
14.60136
-272.86857
-2.1467
21.51952
7.82421
Finished
-
gaochenxiao
5m 37s
-
numpy.float32
float32
torch.float32
256
false
true
0.99
10
10
256
0.0003
10
false
1
1000
d4rl
false
false
50
2
1000
halfcheetah-medium-v2
0.005
0.33
lamda-rl
InAC-D4RL
["cuda:11","cuda:12","cuda:13","cuda:14","cuda:15"]
1000
0
48.11144
0.569
-1130.55103
-2.49946
60.25171
11.46952
Finished
-
gaochenxiao
8m 10s
-
numpy.float32
float32
torch.float32
256
false
true
0.99
10
10
256
0.0003
10
false
1
1000
d4rl
false
false
50
2
1000
hopper-medium-expert-v2
0.005
0.01
lamda-rl
InAC-D4RL
["cuda:11","cuda:12","cuda:13","cuda:14","cuda:15"]
777.26
168.56923
87.56973
19.77318
-1421.05532
-0.20168
6.85452
2.38066
Finished
-
gaochenxiao
5m 49s
-
numpy.float32
float32
torch.float32
256
false
true
0.99
10
10
256
0.0003
10
false
1
1000
d4rl
false
false
50
2
1000
walker2d-medium-replay-v2
0.005
0.5
lamda-rl
InAC-D4RL
["cuda:11","cuda:12","cuda:13","cuda:14","cuda:15"]
1000
0
75.22471
1.58238
2403.58728
1.43146
73.09202
23.2559
Finished
-
gaochenxiao
5m 57s
-
numpy.float32
float32
torch.float32
256
false
true
0.99
10
10
256
0.0003
10
false
1
1000
d4rl
false
false
50
2
1000
walker2d-expert-v2
0.005
0.01
lamda-rl
InAC-D4RL
["cuda:11","cuda:12","cuda:13","cuda:14","cuda:15"]
1000
0
112.24302
0.18984
-6668.121
-2.84808
1.61837
0.48627
Finished
-
gaochenxiao
4m 2s
-
numpy.float32
float32
torch.float32
256
false
true
0.99
10
10
256
0.0003
10
false
1
1000
d4rl
false
false
50
2
1000
halfcheetah-medium-expert-v2
0.005
0.1
lamda-rl
InAC-D4RL
["cuda:11","cuda:12","cuda:13","cuda:14","cuda:15"]
1000
0
93.71822
0.9778
-8043.27686
-2.312
294.32796
74.25432
Finished
-
gaochenxiao
3m 56s
-
numpy.float32
float32
torch.float32
256
false
true
0.99
10
10
256
0.0003
10
false
1
1000
d4rl
false
false
50
2
1000
hopper-medium-v2
0.005
0.1
lamda-rl
InAC-D4RL
["cuda:11","cuda:12","cuda:13","cuda:14","cuda:15"]
658.48
111.91648
67.80374
11.53665
-361.86483
-0.40729
4.52176
1.65011
Finished
-
gaochenxiao
5m 15s
-
numpy.float32
float32
torch.float32
256
false
true
0.99
10
10
256
0.0003
10
false
1
1000
d4rl
false
false
50
2
1000
halfcheetah-expert-v2
0.005
0.01
lamda-rl
InAC-D4RL
["cuda:11","cuda:12","cuda:13","cuda:14","cuda:15"]
1000
0
95.10247
0.80679
-14845.31504
-3.21549
50.68732
10.98609
Finished
-
gaochenxiao
5m 14s
-
numpy.float32
float32
torch.float32
256
false
true
0.99
10
10
256
0.0003
10
false
1
1000
d4rl
false
false
50
2
1000
walker2d-medium-expert-v2
0.005
0.1
lamda-rl
InAC-D4RL
["cuda:11","cuda:12","cuda:13","cuda:14","cuda:15"]
1000
0
110.92388
0.51031
-5237.50796
-2.177
32.56938
10.91586
1-12
of 12