Howuhh's group workspace
Group: small_scale_iql_chaotic_lstm_multiseed-v0
Name
114 visualized
alpha: null
alpha: null
114
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
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
0.999
0.005
-
0.8
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
1-1
of 1