Howuhh's group workspace
Group: long_small_scale_cql_chaotic_lstm_multiseed-v0
Name
1 visualized
alpha: 2
alpha: 2
1
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
-
-
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
1-1
of 1