Howuhh's group workspace
Group: small_scale_cql_chaotic_lstm_sweep-v1
Name
24 visualized
alpha: 1
alpha: 1
3
alpha: 0.5
alpha: 0.5
3
alpha: 0.10000000000000002
alpha: 0.10000000000000002
3
alpha: 0.01
alpha: 0.01
3
alpha: 0.05000000000000001
alpha: 0.05000000000000001
3
alpha: 0.001
alpha: 0.001
3
alpha: 0.0005
alpha: 0.0005
3
alpha: 0.0001
alpha: 0.0001
3
State
Notes
User
Tags
Created
Runtime
Sweep
batch_size
character
checkpoints_path
data_mode
eval_episodes
eval_every
eval_processes
eval_seed
group
learning_rate
mlc_job_name
name
project
rnn_dropout
rnn_hidden_dim
rnn_layers
seq_len
train_seed
update_steps
use_prev_action
version
weight_decay
alpha
clip_range
gamma
tau
num_heads
expectile_tau
temperature
depth_max
depth_mean
depth_median
depth_min
depth_std
loss
reward_max
reward_mean
reward_median
reward_min
reward_std
times/backward_pass
times/batch_loading_cpu
times/batch_loading_gpu
times/evaluation_cpu
Finished
howuhh
9h 48m 9s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-27f619cd","cql-mon-hum-neu-504c65d4","cql-mon-hum-neu-ab310df9"]
NetHack
0
2048
2
16
1
250000
true
1
0
1
10
0.999
0.005
-
-
-
0.33333
0.066667
0
0
0.13333
27.18288
11
0.58667
0
0
2.21735
0.014788
0.063963
0.063919
13.67806
Finished
howuhh
6h 56m 8s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
cql-mon-hum-neu-504c65d4
NetHack
0
2048
2
16
2
250000
true
1
0
1
10
0.999
0.005
-
-
-
0
0
0
0
0
16.5666
24
1.18
0
0
4.73155
0.016363
0.078242
0.078194
17.30081
Finished
howuhh
5h 41m 31s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
cql-mon-hum-neu-ab310df9
NetHack
0
2048
2
16
1
250000
true
1
0
1
10
0.999
0.005
-
-
-
0
0
0
0
0
15.98228
5
0.1
0
0
0.7
0.013561
0.041494
0.041456
11.71343
Finished
howuhh
5h 56m 38s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
cql-mon-hum-neu-27f619cd
NetHack
0
2048
2
16
0
250000
true
1
0
1
10
0.999
0.005
-
-
-
1
0.2
0
0
0.4
48.99975
4
0.48
0
0
1.22049
0.014441
0.072152
0.072106
12.01994
Finished
howuhh
6h 5m 59s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-73c07619","cql-mon-hum-neu-9a18f777","cql-mon-hum-neu-b1ee4ee3"]
NetHack
0
2048
2
16
1
250000
true
1
0
0.5
10
0.999
0.005
-
-
-
0
0
0
0
0
1.5156
0
0
0
0
0
0.014079
0.060124
0.060088
11.80019
Finished
howuhh
10h 33m 33s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-0a6c444e","cql-mon-hum-neu-3aa948b7","cql-mon-hum-neu-5e57ebf5"]
NetHack
0
2048
2
16
1
250000
true
1
0
0.1
10
0.999
0.005
-
-
-
0
0
0
0
0
0.46952
407
14.03333
0
0
63.42993
0.015657
0.056987
0.056945
35.96532
Finished
howuhh
6h 5m 52s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-4305f833","cql-mon-hum-neu-5e902af4","cql-mon-hum-neu-c79b7a95"]
NetHack
0
2048
2
16
1
250000
true
1
0
0.01
10
0.999
0.005
-
-
-
1
0.24
0.33333
0
0.28583
9.8631
181.33333
32.42
23.16667
0
34.32517
0.013582
0.046092
0.046058
59.9475
Finished
howuhh
6h 9m
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-5469ca40","cql-mon-hum-neu-8e596a5c","cql-mon-hum-neu-bed7f0b8"]
NetHack
0
2048
2
16
1
250000
true
1
0
0.05
10
0.999
0.005
-
-
-
0.33333
0.013333
0
0
0.06532
0.46286
1141.33333
226.54667
169
0
241.08923
0.01458
0.051477
0.051432
66.6841
Finished
howuhh
11h 49m 38s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-1ee3f6de","cql-mon-hum-neu-5bf2dbfe","cql-mon-hum-neu-5d4b8474"]
NetHack
0
2048
2
16
1
250000
true
1
0
0.001
10
0.999
0.005
-
-
-
1
0.066667
0
0
0.22765
0.34143
2436
395.56
262
0
476.52966
0.014258
0.049918
0.049881
106.84783
Finished
howuhh
7h 31m 37s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-0c2b7503","cql-mon-hum-neu-1b44b90d","cql-mon-hum-neu-83f9c90c"]
NetHack
0
2048
2
16
1
250000
true
1
0
0.0005
10
0.999
0.005
-
-
-
1.33333
0.046667
0
0
0.22583
0.2971
2062
396.5
194.33333
0
488.82128
0.015165
0.057747
0.057705
165.9488
Finished
howuhh
6h 16m 56s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-29d5d55d","cql-mon-hum-neu-70d9d419","cql-mon-hum-neu-bba137a1"]
NetHack
0
2048
2
16
1
250000
true
1
0
0.0001
10
0.999
0.005
-
-
-
1
0.08
0
0
0.25276
0.29705
1796
526.72
395.66667
0
505.87206
0.013682
0.039483
0.039445
127.77946
1-8
of 8