Hashimoto's workspace
Runs
48
Name
48 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
action_repeat
batch_size
buffer_size
capture_video
consis_coef
env_id
exp_name
exploration_noise
gamma
horizon
iterations
latent_dim
learning_rate
learning_starts
num_actor_traj
num_elites
num_samples
policy_frequency
reward_coef
rho
seed
target_network_frequency
tau
temperature
total_timesteps
track
value_coef
wandb_project_name
charts/SPS
charts/average_reward
charts/episodic_length
charts/episodic_return
global_step
losses/actor_loss
losses/qf1_loss
losses/qf1_values
losses/qf2_loss
losses/qf2_values
losses/reward_loss
losses/transition_loss
Crashed
Finished
hashimoto
7d 15h 57m 32s
-
2
512
1000000
true
-
dm_control/walker-run-v0
simple_mlp
0.05
0.99
12.5
10
-
0.0001
25000
-
64
512
-
-
0.5
1
-
-
0.5
3000000
true
-
mlss2024
17.83333
0.70437
500
352.18446
2225128.33333
-
-
-
-
-
0.000058489
0.21072
Finished
hashimoto
1d 19h 46m 38s
-
2
512
-
true
-
dm_control/humanoid-run-v0
simple_mlp
0.05
0.99
10
10
-
0.0001
25000
-
64
512
-
-
0.5
1
-
-
0.5
1000000
true
-
mlss2024
18.33333
0.0014862
500
0.74309
999997
-
-
-
-
-
7.5466e-7
1.08275
Finished
hashimoto
3d 19h 42m 37s
-
4
512
-
true
-
dm_control/quadruped-run-v0
simple_mlp
0.05
0.99
12.5
10
-
0.0001
25000
-
64
512
-
-
0.5
1
-
-
0.5
1000000
true
-
mlss2024
14.5
2.73664
250
684.15989
999985
-
-
-
-
-
0.0011378
0.7016
Finished
hashimoto
2d 6h 42m 35s
-
2
512
-
true
-
dm_control/dog-run-v0
simple_mlp
0.05
0.99
10
10
-
0.0001
25000
-
64
512
-
-
0.5
1
-
-
0.5
1000000
true
-
mlss2024
15
0.010866
500
5.43282
999997
-
-
-
-
-
0.000051092
59.58375
Finished
hashimoto
6d 21h 30m 16s
-
4
768
1000000
true
-
dm_control/cheetah-run-v0
simple_mlp
0.05
0.99
12.5
10
-
0.0001
25000
-
64
768
-
-
0.5
1
-
-
0.5
1000000
true
-
mlss2024
14.5
2.33902
250
584.75498
999985
-
-
-
-
-
0.00047086
0.049054
Finished
hashimoto
6d 14h 45m 19s
-
2
512
1000000
true
2
dm_control/dog-run-v0
tdmpc
0.05
0.99
3
6
64
0.001
25000
16
64
512
-
0.5
0.5
1
2
0.01
0.5
3000000
true
0.1
mlss2024
79.16667
0.1551
500
77.55153
2999988
-15218.8291
3747376.16644
25676.87545
3493072.50074
25710.60086
0.00038127
219.48432
Finished
hashimoto
4d 15h 10m 56s
-
2
512
1000000
true
2
dm_control/humanoid-run-v0
tdmpc
0.05
0.99
3
6
64
0.001
25000
16
64
512
-
0.5
0.5
1
2
0.01
0.5
3000000
true
0.1
mlss2024
96.16667
0.60698
500
303.49059
2999988
-68.76865
0.29589
117.12576
0.29763
117.11893
0.00025947
1.01534
Finished
hashimoto
3d 1h 4m 19s
-
2
512
1000000
true
2
dm_control/walker-run-v0
tdmpc
0.05
0.99
3
6
64
0.001
25000
16
64
512
1
0.5
0.5
1
2
0.01
0.5
3000000
true
0.1
mlss2024
105.66667
1.69079
500
845.39393
2999988
-103.96578
0.012411
178.06551
0.012505
178.06984
0.000044722
0.14001
Finished
hashimoto
4h 30m 41s
-
4
512
1000000
true
2
dm_control/quadruped-run-v0
tdmpc
0.05
0.99
3
6
64
0.001
25000
16
64
512
-
0.5
0.5
1
2
0.01
0.5
1000000
true
0.1
mlss2024
185
3.71327
250
928.31875
999984
-230.92214
0.055687
395.27226
0.057387
395.26859
0.00038749
0.22279
Finished
hashimoto
3h 48m 41s
-
4
512
1000000
true
2
dm_control/cheetah-run-v0
tdmpc
0.05
0.99
3
6
64
0.001
25000
16
64
512
1
0.5
0.5
1
2
0.01
0.5
1000000
true
0.1
mlss2024
219.33333
2.54923
250
637.3067
999984
-205.83935
1.89183
351.26556
1.96587
351.22219
0.0010194
0.55868
1-10
of 10