Gaochenxiao's workspace
Runs
56
Name
5 visualized
env: maze2d-umaze-v1
env: maze2d-umaze-v1
1
1
env: Walker-Run-v1
env: Walker-Run-v1
1
5
env: Quadruped-Run-v1
env: Quadruped-Run-v1
1
5
env: Hopper-Hop-v1
env: Hopper-Hop-v1
1
5
env: Acrobot-Swingup-v1
env: Acrobot-Swingup-v1
1
5
env: Cheetah-Run-v1
env: Cheetah-Run-v1
1
5
env: Swimmer-v3
env: Swimmer-v3
1
5
env: Humanoid-v3
env: Humanoid-v3
1
5
env: HalfCheetah-v3
env: HalfCheetah-v3
1
5
env: Walker2d-v3
env: Walker2d-v3
1
5
env: Hopper-v3
env: Hopper-v3
1
5
env: Ant-v3
env: Ant-v3
1
5
State
Notes
User
Tags
Created
Runtime
Sweep
UtilsRL.numpy_fp
UtilsRL.precision
UtilsRL.torch_fp
actor_lr
actor_update_interval
batch_size
critic_lr
debug
device
discount
env
env_type
eval_episode
eval_interval
exploration_noise
hidden_dims
log_interval
max_buffer_size
max_trajectory_length
name
noise_clip
num_epoch
policy_noise
random_policy_epoch
save_interval
seed
step_per_epoch
task
tau
wandb.entity
wandb.project
domain
Eval/episode_return_mean
Eval/episode_return_std
Eval/length_mean
Eval/length_std
loss/actor_loss
loss/q_loss
rollout/episode_length
rollout/episode_return
Killed
-
kongrui
12s
-
numpy.float32
float32
torch.float32
0.0003
2
256
0.0003
false
-
0.99
maze2d-umaze-v1
mujoco
10
10
0.1
256
10
1000000
1000
maze2d
0.5
300
0.2
25
50
0
1000
maze2d-umaze-v1
0.005
LAMDA-RL
td3-online
-
-
-
-
-
-
-
-
-
Finished
-
gaochenxiao
2d 7h 21m 44s
-
numpy.float32
float32
torch.float32
0.0001
2
1024
0.0001
false
["cuda:0","cuda:1"]
0.99
Walker-Run-v1
dmc
10
10
0.1
1024
10
1000000
1000
dmc
0.5
2000
0.2
25
50
2
1000
run
0.005
lamda-rl
TD3-Online
walker
814.3016
14.80811
1000
0
-78.5225
0.020543
1000
792.68206
Finished
-
gaochenxiao
2d 4h 30m 1s
-
numpy.float32
float32
torch.float32
0.0001
2
1024
0.0001
false
["cuda:0","cuda:1"]
0.99
Quadruped-Run-v1
dmc
10
10
0.1
1024
10
1000000
1000
dmc
0.5
2000
0.2
25
50
2
1000
run
0.005
lamda-rl
TD3-Online
quadruped
842.70616
102.45888
1000
0
-81.19346
0.084124
1000
903.03807
Finished
-
gaochenxiao
2d 45m 57s
-
numpy.float32
float32
torch.float32
0.0001
2
1024
0.0001
false
["cuda:0","cuda:1"]
0.99
Hopper-Hop-v1
dmc
10
10
0.1
1024
10
1000000
1000
dmc
0.5
2000
0.2
25
50
2
1000
hop
0.005
lamda-rl
TD3-Online
hopper
271.17002
6.1732
1000
0
-23.77093
0.020209
1000
257.19911
Finished
-
gaochenxiao
1d 3h 56m 10s
-
numpy.float32
float32
torch.float32
0.0001
2
1024
0.0001
false
["cuda:0","cuda:1"]
0.99
Acrobot-Swingup-v1
dmc
10
10
0.1
1024
10
1000000
1000
dmc
0.5
2000
0.2
25
50
2
1000
swingup
0.005
lamda-rl
TD3-Online
acrobot
263.33183
338.56684
1000
0
-25.40509
0.066769
1000
606.45683
Finished
-
gaochenxiao
1d 13h 29m 49s
-
numpy.float32
float32
torch.float32
0.0001
2
1024
0.0001
false
["cuda:0","cuda:1"]
0.99
Cheetah-Run-v1
dmc
10
10
0.1
1024
10
1000000
1000
dmc
0.5
2000
0.2
25
50
2
1000
run
0.005
lamda-rl
TD3-Online
cheetah
904.74897
6.11236
1000
0
-89.69169
0.038196
1000
895.44438
Finished
-
gaochenxiao
13m 16s
-
numpy.float32
float32
torch.float32
0.0003
2
256
0.0003
false
["cuda:0","cuda:1"]
0.99
Swimmer-v3
mujoco
10
10
0.1
256
10
1000000
1000
mujoco
0.5
3000
0.2
25
50
2
1000
Swimmer-v3
0.005
lamda-rl
TD3-Online
-
139.56799
4.77428
1000
0
-10.72871
0.0014493
1000
137.68385
Finished
-
gaochenxiao
6m 32s
-
numpy.float32
float32
torch.float32
0.0003
2
256
0.0003
false
["cuda:0","cuda:1"]
0.99
Humanoid-v3
mujoco
10
10
0.1
256
10
1000000
1000
mujoco
0.5
3000
0.2
25
50
2
1000
Humanoid-v3
0.005
lamda-rl
TD3-Online
-
6088.6274
31.62704
1000
0
-568.68849
24.60383
1000
6127.29266
Finished
-
gaochenxiao
12m 27s
-
numpy.float32
float32
torch.float32
0.0003
2
256
0.0003
false
["cuda:0","cuda:1"]
0.99
HalfCheetah-v3
mujoco
10
10
0.1
256
10
1000000
1000
mujoco
0.5
3000
0.2
25
50
2
1000
HalfCheetah-v3
0.005
lamda-rl
TD3-Online
-
14224.18029
162.50913
1000
0
-1089.87144
211.05157
1000
13089.26179
Finished
-
gaochenxiao
4m 22s
-
numpy.float32
float32
torch.float32
0.0003
2
256
0.0003
false
["cuda:0","cuda:1"]
0.99
Walker2d-v3
mujoco
10
10
0.1
256
10
1000000
1000
mujoco
0.5
3000
0.2
25
50
2
1000
Walker2d-v3
0.005
lamda-rl
TD3-Online
-
4821.79243
388.77795
969.38
52.90591
-470.62452
16.33034
1000
4980.29513
Finished
-
gaochenxiao
12m 20s
-
numpy.float32
float32
torch.float32
0.0003
2
256
0.0003
false
["cuda:0","cuda:1"]
0.99
Hopper-v3
mujoco
10
10
0.1
256
10
1000000
1000
mujoco
0.5
3000
0.2
25
50
2
1000
Hopper-v3
0.005
lamda-rl
TD3-Online
-
3460.96063
460.0016
918.42
114.06388
-351.74422
14.07385
933.2
3483.4841
Finished
-
gaochenxiao
11m 10s
-
numpy.float32
float32
torch.float32
0.0003
2
256
0.0003
false
["cuda:0","cuda:1"]
0.99
Ant-v3
mujoco
10
10
0.1
256
10
1000000
1000
mujoco
0.5
3000
0.2
25
50
2
1000
Ant-v3
0.005
lamda-rl
TD3-Online
-
6373.10959
123.08021
997.72
6.84
-481.31761
43.70729
1000
5994.3763
1-12
of 12