Clabornd's group workspace
Group: train_2023-07-08_19-56-28
State
Notes
User
Tags
Created
Runtime
Sweep
actor_lr
batch_size
buffer_size
critic_lr
epochs
eps
explore_0
explore_decay
gamma
lam
min_explore
run_id
samples_per_epoch
trial_log_path
wandb.project
epoch_avg_rew
Crashed
-
clabornd
10h 18m 38s
-
0.00073922
256
50000
0.00053215
100
0.21549
0.95
0.95
0.98714
0.84445
0.05
-
10000
/root/ray_results/train_2023-07-08_19-56-28/train_86c91_00002_2_actor_lr=0.0007,critic_lr=0.0005,eps=0.2155,gamma=0.9871,lam=0.8444_2023-07-08_19-56-28
ppo-basic
-
Crashed
-
clabornd
10h 18m 37s
-
0.00084544
256
50000
0.00067097
100
0.08789
0.95
0.95
0.99388
0.62976
0.05
-
10000
/root/ray_results/train_2023-07-08_19-56-28/train_86c91_00001_1_actor_lr=0.0008,critic_lr=0.0007,eps=0.0879,gamma=0.9939,lam=0.6298_2023-07-08_19-56-28
ppo-basic
-
Crashed
-
clabornd
10h 18m 38s
-
0.00063829
256
50000
0.00086172
100
0.10682
0.95
0.95
0.99719
0.59904
0.05
-
10000
/root/ray_results/train_2023-07-08_19-56-28/train_86c91_00003_3_actor_lr=0.0006,critic_lr=0.0009,eps=0.1068,gamma=0.9972,lam=0.5990_2023-07-08_19-56-28
ppo-basic
-
Crashed
-
clabornd
10h 18m 39s
-
0.00079827
256
50000
0.00082805
100
0.11553
0.95
0.95
0.98953
0.92609
0.05
-
10000
/root/ray_results/train_2023-07-08_19-56-28/train_86c91_00000_0_actor_lr=0.0008,critic_lr=0.0008,eps=0.1155,gamma=0.9895,lam=0.9261_2023-07-08_19-56-28
ppo-basic
-
1-4
of 4