Howuhh's group workspace
Group: small_scale_cql_chaotic_lstm_multiseed-v0
Name
114 visualized
alpha: 0.0001
alpha: 0.0001
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
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
1-1
of 1