Costa-huang's workspace
Runs
1,210
Name
1,210 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
anneal_lr
batch_size
capture_video
clip_coef
clip_vloss
cuda
ent_coef
exp_name
gae
gae_lambda
gamma
gym_id
kle_rollback
kle_stop
learning_rate
max_grad_norm
minibatch_size
n_minibatch
norm_adv
num_envs
num_steps
prod_mode
seed
target_kl
torch_deterministic
total_timesteps
update_epochs
vf_coef
wandb_project_name
charts/episode_reward
charts/learning_rate
debug/pg_stop_iter
global_step
losses/approx_kl
losses/entropy
losses/policy_loss
losses/value_loss
Finished
-
neurips2020-early-stopping
1h 59m 45s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-stop-0.05
true
0.95
0.99
Humanoid-v2
false
true
0.0003
0.5
64
32
true
1
2048
true
2
0.05
true
2000000
80
0.5
ppo-early-stopping2
1173.36365
3.0738e-7
79
1998848
-0.011494
12.21265
-0.030574
0.010783
Finished
-
neurips2020-early-stopping
1h 58m 10s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-stop-0.05
true
0.95
0.99
Humanoid-v2
false
true
0.0003
0.5
64
32
true
1
2048
true
1
0.05
true
2000000
80
0.5
ppo-early-stopping2
1030.46692
3.0738e-7
79
1998848
0.0049348
10.63911
-0.029829
0.017399
Finished
-
neurips2020-early-stopping
1h 54m 30s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-stop-0.03
true
0.95
0.99
Humanoid-v2
false
true
0.0003
0.5
64
32
true
1
2048
true
1
0.03
true
2000000
80
0.5
ppo-early-stopping2
1354.07166
3.0738e-7
79
1998848
-0.0017672
16.99576
-0.022248
0.014183
Finished
-
neurips2020-early-stopping
1h 1m 9s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-stop-0.03
true
0.95
0.99
Humanoid-v2
false
true
0.0003
0.5
64
32
true
1
2048
true
2
0.03
true
2000000
80
0.5
ppo-early-stopping2
2144.87378
3.0738e-7
79
1998848
0.0038866
16.35703
-0.013764
0.007953
Finished
-
neurips2020-early-stopping
1h 1m 32s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-stop-0.025
true
0.95
0.99
Humanoid-v2
false
true
0.0003
0.5
64
32
true
1
2048
true
1
0.025
true
2000000
80
0.5
ppo-early-stopping2
698.99207
3.0738e-7
79
1998848
0.0029708
18.3598
-0.029095
0.089733
Finished
-
neurips2020-early-stopping
1h 19m 35s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-stop-0.025
true
0.95
0.99
Humanoid-v2
false
true
0.0003
0.5
64
32
true
1
2048
true
2
0.025
true
2000000
80
0.5
ppo-early-stopping2
5473.55908
3.0738e-7
79
1998848
-0.0017663
15.25997
-0.040057
0.037119
Finished
-
neurips2020-early-stopping
58m 23s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-stop-0.02
true
0.95
0.99
Humanoid-v2
false
true
0.0003
0.5
64
32
true
1
2048
true
2
0.02
true
2000000
80
0.5
ppo-early-stopping2
1049.41077
3.0738e-7
79
1998848
0.01286
19.30856
-0.022422
0.037529
Finished
-
neurips2020-early-stopping
1h 56s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-stop-0.015
true
0.95
0.99
Humanoid-v2
false
true
0.0003
0.5
64
32
true
1
2048
true
1
0.015
true
2000000
80
0.5
ppo-early-stopping2
2571.09082
3.0738e-7
79
1998848
0.006527
20.18456
-0.005718
0.0070561
Finished
-
neurips2020-early-stopping
1h 28m 3s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-stop-0.015
true
0.95
0.99
Humanoid-v2
false
true
0.0003
0.5
64
32
true
1
2048
true
2
0.015
true
2000000
80
0.5
ppo-early-stopping2
3776.50244
3.0738e-7
79
1998848
-0.0046113
20.13175
-0.019037
0.033232
Finished
-
neurips2020-early-stopping
1h 4m 29s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-stop-0.02
true
0.95
0.99
Humanoid-v2
false
true
0.0003
0.5
64
32
true
1
2048
true
1
0.02
true
2000000
80
0.5
ppo-early-stopping2
5246.68457
3.0738e-7
79
1998848
0.00068682
18.86385
-0.01867
0.012373
Finished
-
neurips2020-early-stopping
1h 22m 49s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-rollback-0.025
true
0.95
0.99
Humanoid-v2
true
false
0.0003
0.5
64
32
true
1
2048
true
2
0.025
true
2000000
80
0.5
ppo-early-stopping2
2497.60693
3.0738e-7
79
1998848
0.0043619
19.32007
-0.021278
0.016487
Finished
-
neurips2020-early-stopping
1h 9m 4s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-rollback-0.05
true
0.95
0.99
Humanoid-v2
true
false
0.0003
0.5
64
32
true
1
2048
true
2
0.05
true
2000000
80
0.5
ppo-early-stopping2
1526.05164
3.0738e-7
79
1998848
0.0067273
11.87835
-0.045769
0.020938
Finished
-
neurips2020-early-stopping
1h 49m 14s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-rollback-0.015
true
0.95
0.99
Humanoid-v2
true
false
0.0003
0.5
64
32
true
1
2048
true
2
0.015
true
2000000
80
0.5
ppo-early-stopping2
971.76208
3.0738e-7
79
1998848
0.0012912
21.16389
-0.017357
0.021775
Finished
-
neurips2020-early-stopping
1h 12m 3s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-rollback-0.02
true
0.95
0.99
Humanoid-v2
true
false
0.0003
0.5
64
32
true
1
2048
true
1
0.02
true
2000000
80
0.5
ppo-early-stopping2
1408.01953
3.0738e-7
79
1998848
-0.0020488
19.6666
-0.0087335
0.01194
Finished
-
neurips2020-early-stopping
59m 28s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-rollback-0.03
true
0.95
0.99
Humanoid-v2
true
false
0.0003
0.5
64
32
true
1
2048
true
1
0.03
true
2000000
80
0.5
ppo-early-stopping2
1384.78406
3.0738e-7
79
1998848
-0.012168
18.30544
-0.031318
0.016461
Finished
-
neurips2020-early-stopping
1h 58m 40s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-rollback-0.015
true
0.95
0.99
Humanoid-v2
true
false
0.0003
0.5
64
32
true
1
2048
true
1
0.015
true
2000000
80
0.5
ppo-early-stopping2
798.78113
3.0738e-7
79
1998848
-0.0061692
21.52287
-0.011962
0.020954
Finished
-
neurips2020-early-stopping
1h 1m 23s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-rollback-0.03
true
0.95
0.99
Humanoid-v2
true
false
0.0003
0.5
64
32
true
1
2048
true
2
0.03
true
2000000
80
0.5
ppo-early-stopping2
912.62738
3.0738e-7
79
1998848
0.012384
18.1044
-0.018908
0.012203
Finished
-
neurips2020-early-stopping
1h 5m 43s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-rollback-0.05
true
0.95
0.99
Humanoid-v2
true
false
0.0003
0.5
64
32
true
1
2048
true
1
0.05
true
2000000
80
0.5
ppo-early-stopping2
1247.23975
3.0738e-7
79
1998848
-0.004843
13.46427
-0.039869
0.029223
Finished
-
neurips2020-early-stopping
1h 3m 35s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-rollback-0.025
true
0.95
0.99
Humanoid-v2
true
false
0.0003
0.5
64
32
true
1
2048
true
1
0.025
true
2000000
80
0.5
ppo-early-stopping2
877.44714
3.0738e-7
79
1998848
0.0011642
17.88853
-0.0096237
0.020711
Finished
-
neurips2020-early-stopping
1h 2m 14s
-
true
2048
true
0.2
true
true
0
m-aggr-kle-rollback-0.02
true
0.95
0.99
Humanoid-v2
true
false
0.0003
0.5
64
32
true
1
2048
true
2
0.02
true
2000000
80
0.5
ppo-early-stopping2
1450.1709
3.0738e-7
79
1998848
0.00065963
20.49366
-0.016149
0.012441
1-20
of 1,210