Howuhh's group workspace
Group: small_scale_cql_chaotic_lstm_sweep-v0
Name
33 visualized
alpha: 5000
alpha: 5000
3
alpha: 1000
alpha: 1000
3
alpha: 500
alpha: 500
3
alpha: 250
alpha: 250
3
alpha: 100
alpha: 100
3
alpha: 50
alpha: 50
3
alpha: 25
alpha: 25
3
alpha: 10
alpha: 10
3
alpha: 5
alpha: 5
3
alpha: 3
alpha: 3
3
alpha: 1
alpha: 1
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
10h 25m 21s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-05711ccb","cql-mon-hum-neu-9d1951bb","cql-mon-hum-neu-a1e30f02"]
NetHack
0
2048
2
16
1
250000
true
0
0
5000
10
0.999
0.005
-
-
-
1.33333
0.08
0
0
0.29098
1473.09501
2865
636.87333
476.33333
1.33333
596.33002
0.01594
0.060211
0.060159
141.2515
Finished
-
howuhh
8h 15m 51s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-20ced03a","cql-mon-hum-neu-4a0153fa","cql-mon-hum-neu-b48d4732"]
NetHack
0
2048
2
16
1
250000
true
0
0
1000
10
0.999
0.005
-
-
-
1
0.04
0
0
0.19115
320.85563
2540.33333
415.2
253
0
518.34477
0.013946
0.050079
0.050044
104.36338
Finished
-
howuhh
7h 47m 32s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-1f86d29e","cql-mon-hum-neu-8a9d31a0","cql-mon-hum-neu-ccc3d0f4"]
NetHack
0
2048
2
16
1
250000
true
0
0
500
10
0.999
0.005
-
-
-
0.66667
0.046667
0
0
0.16959
179.76895
1587.66667
276.92
150.5
0
347.56089
0.014024
0.047157
0.047119
102.73025
Finished
-
howuhh
6h 31m 42s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-827498b7","cql-mon-hum-neu-9c76339c","cql-mon-hum-neu-d2416754"]
NetHack
0
2048
2
16
1
250000
true
0
0
250
10
0.999
0.005
-
-
-
1.33333
0.12667
0
0
0.33655
149.52891
862
116.94667
50
0
159.98778
0.014026
0.053109
0.053073
57.03259
Finished
-
howuhh
7h 44m 8s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-1b7cafd0","cql-mon-hum-neu-2e840d3e","cql-mon-hum-neu-b315f29b"]
NetHack
0
2048
2
16
1
250000
true
0
0
100
10
0.999
0.005
-
-
-
0.66667
0.08
0
0
0.21664
5453.69092
40
1.55333
0
0
6.01544
0.013781
0.047434
0.047396
22.49903
Finished
-
howuhh
13h 25m 51s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-988909a5","cql-mon-hum-neu-bef52290","cql-mon-hum-neu-def09a78"]
NetHack
0
2048
2
16
1
250000
true
0
0
50
10
0.999
0.005
-
-
-
0
0
0
0
0
3691.2173
2.66667
0.19333
0
0
0.51247
0.015061
0.072785
0.072751
15.13829
Finished
-
howuhh
8h 33m 12s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-365ab6ef","cql-mon-hum-neu-4b0242d1","cql-mon-hum-neu-eea8c892"]
NetHack
0
2048
2
16
1
250000
true
0
0
25
10
0.999
0.005
-
-
-
0.66667
0.1
0
0
0.21153
435.93039
664.33333
83.49333
37.16667
0
138.50761
0.016015
0.073746
0.073694
66.19569
Finished
-
howuhh
7h 28m 29s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-2881a882","cql-mon-hum-neu-4775ee9a","cql-mon-hum-neu-62669fe7"]
NetHack
0
2048
2
16
1
250000
true
0
0
10
10
0.999
0.005
-
-
-
1
0.073333
0
0
0.2257
4.7809
1365.66667
239.38
142.66667
0
292.57584
0.015306
0.062194
0.062149
65.96778
Finished
-
howuhh
8h 18m 45s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-0d57a087","cql-mon-hum-neu-368afb39","cql-mon-hum-neu-a107658e"]
NetHack
0
2048
2
16
1
250000
true
0
0
5
10
0.999
0.005
-
-
-
0.33333
0.04
0
0
0.10832
2.74062
209.33333
33.13333
13.16667
0
43.39575
0.015794
0.059928
0.059885
19.0986
Finished
-
howuhh
8h 7m 46s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-833d0b1a","cql-mon-hum-neu-b9ba3058","cql-mon-hum-neu-e60fa391"]
NetHack
0
2048
2
16
1
250000
true
0
0
3
10
0.999
0.005
-
-
-
0
0
0
0
0
1.77388
0
0
0
0
0
0.015063
0.066047
0.066011
11.29323
Finished
-
howuhh
7h 3m 5s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
["cql-mon-hum-neu-1510a68f","cql-mon-hum-neu-393a1b46","cql-mon-hum-neu-79d085b4"]
NetHack
0
2048
2
16
1
250000
true
0
0
1
10
0.999
0.005
-
-
-
0.33333
0.02
0
0
0.079162
106.0807
8
0.26667
0
0
1.33333
0.01532
0.076576
0.076538
12.59383
Finished
-
howuhh
6h 50m 24s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
cql-mon-hum-neu-79d085b4
NetHack
0
2048
2
16
2
250000
true
0
0
1
10
0.999
0.005
-
-
-
0
0
0
0
0
16.5666
24
0.8
0
0
4
0.016496
0.065918
0.065876
15.16509
Finished
-
howuhh
7h 2m 44s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
cql-mon-hum-neu-393a1b46
NetHack
0
2048
2
16
1
250000
true
0
0
1
10
0.999
0.005
-
-
-
1
0.06
0
0
0.23749
145.88626
0
0
0
0
0
0.013557
0.075322
0.075285
11.60271
Finished
-
howuhh
6h 56m 23s
64
mon-hum-neu
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_sweep
0.0003
-
cql-mon-hum-neu-1510a68f
NetHack
0
2048
2
16
0
250000
true
0
0
1
10
0.999
0.005
-
-
-
0
0
0
0
0
155.78925
0
0
0
0
0
0.015906
0.088487
0.088452
11.01369
1-11
of 11