Howuhh's workspace
Runs
746
Name
114 visualized
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
expectile_tau
gamma
num_heads
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
Failed
-
-
4d 7h 18m 41s
64
mon-hum-neu
-
memmap
50
10000
14
50
long_small_scale_iql_chaotic_lstm_multiseed
0.0003
-
iql-mon-hum-neu-80bb81ee
NetHack
0
2048
2
16
0
6600000
true
0
0
-
10
0.8
0.999
-
0.005
1
1
0.1
0
0
0.3
1136.61023
24
0.8
0
0
4
0.014198
0.059153
0.059117
17.40382
Finished
-
-
6d 16h 3m 19s
64
mon-hum-neu
-
memmap
50
10000
14
50
long_small_scale_rem_chaotic_lstm_multiseed
0.0003
-
rem-mon-hum-neu-7cc4da66
NetHack
0
2048
2
16
0
6600000
true
0
0
-
10
-
0.999
200
0.005
-
0
0
0
0
0
NaN
0
0
0
0
0
0.0133
0.071566
0.071526
14.10124
Failed
-
-
4d 15h 15m 56s
64
mon-hum-neu
-
memmap
50
10000
14
50
long_small_scale_awac_chaotic_lstm_multiseed
0.0003
-
awac-mon-hum-neu-c1b62a5c
NetHack
0
2048
2
16
0
6600000
true
0
0
-
10
-
0.999
-
0.005
1
1
0.72
1
0
0.449
2088.84985
0
0
0
0
0
0.018398
0.055794
0.05574
11.14783
Finished
-
-
6d 15h 50m 55s
64
mon-hum-neu
-
memmap
50
10000
14
50
long_small_scale_cql_chaotic_lstm_multiseed
0.0003
-
cql-mon-hum-neu-79d8c1f8
NetHack
0
2048
2
16
0
6600000
true
0
0
2
10
-
0.999
-
0.005
-
0
0
0
0
0
NaN
24
1.12
0
0
4.73557
0.012409
0.04246
0.042419
13.01843
Failed
-
-
2d 21h 43m 9s
64
mon-hum-neu
-
memmap
50
10000
14
50
long_small_scale_bc_chaotic_lstm_multiseed
0.0003
-
bc-mon-hum-neu-fb02153d
NetHack
0
2048
2
16
0
6600000
true
0
0
-
-
-
-
-
-
-
1
0.08
0
0
0.27129
0.64578
607
41.22
0.5
0
103.00316
0.011403
0.019611
0.019574
44.29011
Finished
-
howuhh
2d 12h 50m 43s
64
["kni-hum-law","ran-elf-cha","sam-hum-law","val-dwa-law","val-hum-law","wiz-elf-cha","wiz-gno-neu","wiz-hum-cha","wiz-hum-neu","wiz-orc-cha"]
-
memmap
50
10000
14
50
small_scale_iql_chaotic_lstm_multiseed
0.0003
-
["iql-kni-hum-law-0b2999f3","iql-ran-elf-cha-03d93382","iql-sam-hum-law-f7dca454","iql-wiz-elf-cha-49a6087f","iql-wiz-gno-neu-7513fcc4","iql-wiz-gno-neu-7f42f589","iql-wiz-gno-neu-f3f2d0e7","iql-wiz-orc-cha-20265cab","iql-wiz-orc-cha-7c56a6ef","iql-wiz-orc-cha-9f830dbe"]
NetHack
0
2048
2
16
1
500000
true
0
0
-
10
0.8
0.999
-
0.005
1
0.7193
0.024737
0
0
0.12386
0.24518
2216.5614
478.70193
328.67982
2.42105
490.98278
0.014515
0.053139
0.0531
104.99254
Finished
-
howuhh
2d 21h 7m 59s
64
["kni-hum-law","pri-elf-cha","val-dwa-law","val-hum-law","val-hum-neu","wiz-elf-cha","wiz-gno-neu","wiz-hum-cha","wiz-hum-neu","wiz-orc-cha"]
-
memmap
50
10000
14
50
small_scale_awac_chaotic_lstm_multiseed
0.0003
-
["awac-kni-hum-law-8b7dca62","awac-pri-elf-cha-be3cd198","awac-wiz-elf-cha-8a20b8d0","awac-wiz-elf-cha-ca4691ff","awac-wiz-gno-neu-12c7428e","awac-wiz-gno-neu-6f65df81","awac-wiz-gno-neu-98c62f36","awac-wiz-orc-cha-0514f22d","awac-wiz-orc-cha-cab38a53","awac-wiz-orc-cha-ee213c70"]
NetHack
0
2048
2
16
1
500000
true
0
0
-
10
-
0.999
-
0.005
1
0.64912
0.021579
0
0
0.11136
0.22646
2326.40351
511.20596
351.19737
2.88596
522.70602
0.015029
0.058862
0.058819
109.94654
Finished
-
howuhh
3d 15h 25m 14s
64
["kni-hum-law","tou-hum-neu","val-dwa-law","val-hum-law","val-hum-neu","wiz-elf-cha","wiz-gno-neu","wiz-hum-cha","wiz-hum-neu","wiz-orc-cha"]
-
memmap
50
10000
14
50
small_scale_rem_chaotic_lstm_multiseed
0.0003
-
["rem-kni-hum-law-8527bf90","rem-kni-hum-law-e5adf352","rem-wiz-elf-cha-203b572e","rem-wiz-elf-cha-3a085d2a","rem-wiz-gno-neu-2dedfdb5","rem-wiz-gno-neu-73279636","rem-wiz-gno-neu-87c5a200","rem-wiz-orc-cha-0cd295b5","rem-wiz-orc-cha-176e6ee4","rem-wiz-orc-cha-b2a4b9d8"]
NetHack
0
2048
2
16
1
500000
true
0
0
-
10
-
0.999
200
0.005
-
0.0087719
0.0012281
0
0
0.0030437
670.27355
0.026316
0.00052632
0
0
0.0036842
0.019971
0.056184
0.05614
13.32607
Finished
-
howuhh
4d 9h 40m 17s
64
["cav-dwa-law","kni-hum-law","pri-hum-cha","ran-hum-neu","val-hum-neu","wiz-elf-cha","wiz-gno-neu","wiz-hum-cha","wiz-hum-neu","wiz-orc-cha"]
-
memmap
50
10000
14
50
small_scale_cql_chaotic_lstm_multiseed
0.0003
-
["cql-cav-dwa-law-1f6a1030","cql-kni-hum-law-55fa21cd","cql-kni-hum-law-a8675b63","cql-pri-hum-cha-ae66a4ff","cql-ran-hum-neu-87a5f119","cql-val-hum-neu-bf18451e","cql-wiz-gno-neu-cf3aaaa8","cql-wiz-orc-cha-6ab174f3","cql-wiz-orc-cha-8861f9b3","cql-wiz-orc-cha-a049c08e"]
NetHack
0
2048
2
16
1
500000
true
0
0
0.0001
10
-
0.999
-
0.005
-
0.57018
0.019649
0
0
0.09907
0.23781
2431.51754
493.62474
331.5
2.14035
526.43138
0.014192
0.054985
0.054943
101.73812
Finished
-
howuhh
22h 2m 34s
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-27f619cd","cql-mon-hum-neu-3aa948b7","cql-mon-hum-neu-4305f833","cql-mon-hum-neu-504c65d4","cql-mon-hum-neu-5e57ebf5","cql-mon-hum-neu-73c07619","cql-mon-hum-neu-9a18f777","cql-mon-hum-neu-ab310df9","cql-mon-hum-neu-b1ee4ee3"]
NetHack
0
2048
2
16
1
250000
true
1
0
0.2077
10
-
0.999
-
0.005
-
0.625
0.064167
0.041667
0
0.14884
5.05369
1004.33333
199.04583
130.52083
0
226.53558
0.014474
0.053224
0.053184
73.58141
Finished
-
howuhh
19h 24m 12s
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-1f86d29e","cql-mon-hum-neu-20ced03a","cql-mon-hum-neu-4a0153fa","cql-mon-hum-neu-827498b7","cql-mon-hum-neu-8a9d31a0","cql-mon-hum-neu-9d1951bb","cql-mon-hum-neu-a1e30f02","cql-mon-hum-neu-b48d4732","cql-mon-hum-neu-ccc3d0f4"]
NetHack
0
2048
2
16
1
250000
true
0
0
631.27273
10
-
0.999
-
0.005
-
0.66667
0.055152
0
0
0.16633
1074.49665
922.27273
163.99636
102.07576
0.12121
191.32399
0.014934
0.060842
0.060802
56.19674
Finished
-
howuhh
2d 4h 54m 12s
64
["sam-hum-law","tou-hum-neu","val-dwa-law","val-hum-law","val-hum-neu","wiz-elf-cha","wiz-gno-neu","wiz-hum-cha","wiz-hum-neu","wiz-orc-cha"]
-
memmap
50
10000
14
50
small_scale_bc_chaotic_lstm_multiseed
0.0003
["selectel-a100-1x-katakomba-0vb5pj","selectel-a100-1x-katakomba-6kxohl","selectel-a100-1x-katakomba-bac1vv","selectel-a100-1x-katakomba-dpb5vs","selectel-a100-1x-katakomba-h20z29","selectel-a100-1x-katakomba-te22ju","selectel-a100-1x-katakomba-u9ooe9","selectel-a100-1x-katakomba-vvs1k3","selectel-a100-1x-katakomba-wpd24w","selectel-a100-1x-katakomba-yzxqk7"]
["bc-wiz-elf-cha-7af9fe90","bc-wiz-elf-cha-96d894f2","bc-wiz-elf-cha-9bb00e7e","bc-wiz-gno-neu-42b52cdc","bc-wiz-gno-neu-7b960fba","bc-wiz-gno-neu-c2a5e59b","bc-wiz-hum-cha-fcea7188","bc-wiz-orc-cha-3bcf5516","bc-wiz-orc-cha-509fd8c8","bc-wiz-orc-cha-dffc88ae"]
NetHack
0
2048
2
16
1
500000
true
0
0
-
-
-
-
-
-
-
0.7193
0.027544
0
0
0.1296
0.23898
2258.92982
484.32526
332.20175
1.84211
502.81248
0.011434
0.019922
0.019898
103.45659
Failed
-
howuhh
2d 1h 35m 10s
64
["sam-hum-law","tou-hum-neu","val-dwa-law","val-hum-law","val-hum-neu","wiz-elf-cha","wiz-gno-neu","wiz-hum-cha","wiz-hum-neu","wiz-orc-cha"]
checkpoints
memmap
50
10000
14
50
sweep_v0
0.0003
["selectel-a100-1x-katakomba-4owoes","selectel-a100-1x-katakomba-644y8i","selectel-a100-1x-katakomba-6mota1","selectel-a100-1x-katakomba-atuky7","selectel-a100-1x-katakomba-ehnqlx","selectel-a100-1x-katakomba-r4h76n","selectel-a100-1x-katakomba-sb17k7","selectel-a100-1x-katakomba-t3l4yv","selectel-a100-1x-katakomba-vz58go","selectel-a100-1x-katakomba-y7bb8t"]
["bc-wiz-elf-cha-10c3f3bf","bc-wiz-elf-cha-5c390de9","bc-wiz-elf-cha-5dd9c308","bc-wiz-gno-neu-64b8d0df","bc-wiz-gno-neu-9ef2d730","bc-wiz-gno-neu-fa02ec07","bc-wiz-hum-cha-481ab0b8","bc-wiz-orc-cha-0113573b","bc-wiz-orc-cha-4182a29b","bc-wiz-orc-cha-8a033b90"]
NetHack
0
2048
2
16
1
500000
true
v0
0
-
-
-
-
-
-
-
0.75439
0.025614
0
0
0.12791
0.24066
2441.08772
512.30298
353.01754
2.37719
532.01501
0.011498
0.020324
0.020299
100.13609
1-13
of 13