Mitsuhiko's workspace
Runs
10
Name
10 visualized
env: aloha_cube
env: aloha_cube
5
env: libero
env: libero
5
State
Notes
User
Tags
Created
Runtime
Sweep
action_magnitude
actor_lr
add_states
algorithm
aug_next
batch_size
checkpoint_interval
cnn_features
cnn_padding
cnn_strides
critic_lr
critic_reduction
discount
dropout_rate
encoder_norm
encoder_type
env
env_max_reward
eval_episodes
eval_interval
hidden_dims
latent_dim
launch_group_id
log_interval
max_steps
max_timesteps
multi_grad_step
num_qs
outputdir
prefix
query_freq
resize_image
seed
softmax_temperature
start_online_updates
stochastic_evals
suffix
target_entropy
task_description
tau
temp_lr
train_kwargs.action_magnitude
train_kwargs.actor_lr
train_kwargs.aug_next
Crashed
mitsuhiko
21h 21m 14s
-
2
0.0001
1
pixel_sac
1
256
-1
32
VALID
1.25
0.0003
mean
0.999
0
group
small
aloha_cube
4
10
10000
128
50
500
3000000
400
20
10
["/global/scratch/users/nakamoto/dsrl_pi0_aloha_2025_08_03_15_48_55_0000--s-3","/global/scratch/users/nakamoto/dsrl_pi0_aloha_2025_08_03_15_50_01_0000--s-0","/global/scratch/users/nakamoto/dsrl_pi0_aloha_2025_08_03_15_50_01_0000--s-1","/global/scratch/users/nakamoto/dsrl_pi0_aloha_2025_08_03_15_50_01_0000--s-2","/global/scratch/users/nakamoto/dsrl_pi0_aloha_2025_08_03_15_50_01_0000--s-4"]
dsrl_pi0_aloha
50
64
2
-1
1000
false
auto
-
0.005
0.0003
2
0.0001
1
Failed
mitsuhiko
7h 10m 7s
-
1
0.0001
1
pixel_sac
1
256
-1
32
VALID
1.25
0.0003
mean
0.999
0
group
small
libero
1
10
10000
128
50
500
500000
400
20
10
["/global/scratch/users/nakamoto/dsrl_pi0_libero_2025_08_03_15_37_40_0000--s-0","/global/scratch/users/nakamoto/dsrl_pi0_libero_2025_08_03_15_37_40_0000--s-2","/global/scratch/users/nakamoto/dsrl_pi0_libero_2025_08_03_15_37_57_0000--s-3","/global/scratch/users/nakamoto/dsrl_pi0_libero_2025_08_03_15_37_57_0000--s-4","/global/scratch/users/nakamoto/dsrl_pi0_libero_2025_08_03_15_39_47_0000--s-1"]
dsrl_pi0_libero
20
64
2
-1
500
false
auto
pick up the cream cheese and put it in the tray
0.005
0.0003
1
0.0001
1
1-2
of 2