Caomingjun's workspace
Runs
55
Name
10 visualized
env: Acrobot-Swingup-v1
env: Acrobot-Swingup-v1
5
env: Hopper-Hop-v1
env: Hopper-Hop-v1
5
env: Quadruped-Run-v1
env: Quadruped-Run-v1
5
env: Walker-Run-v1
env: Walker-Run-v1
5
env: Cheetah-Run-v1
env: Cheetah-Run-v1
5
env: Humanoid-v3
env: Humanoid-v3
5
env: Swimmer-v3
env: Swimmer-v3
5
env: Ant-v3
env: Ant-v3
5
env: Hopper-v3
env: Hopper-v3
5
env: HalfCheetah-v3
env: HalfCheetah-v3
5
env: Walker2d-v3
env: Walker2d-v3
5
State
Notes
User
Tags
Created
Runtime
Sweep
UtilsRL.numpy_fp
UtilsRL.precision
UtilsRL.torch_fp
actor_hidden_dims
actor_lr
actor_type
alpha
alpha_lr
auto_alpha
batch_size
critic_hidden_dims
critic_lr
debug
device
discount
domain
env
env_type
eta
eval_episode
eval_interval
gamma
log_interval
max_buffer_size
max_trajectory_length
name
num_epoch
policy_logstd_max
policy_logstd_min
random_policy_epoch
reward_scale
save_interval
seed
step_per_epoch
target_update_freq
task
task_type
tau
wandb.entity
wandb.project
warmup_epoch
critic_q_num
Eval/episode_return_mean
Eval/episode_return_std
Finished
-
gaochenxiao
2m 44s
-
numpy.float32
float32
torch.float32
1024
0.0001
-
0.2
0.0001
true
1024
1024
0.0001
false
-
0.99
acrobot
Acrobot-Swingup-v1
dmc
-
10
10
-
10
1000000
1000
dmc
2000
2
-5
5
1
50
2
1000
2
swingup
-
0.005
lamda-rl
SAC-Online
5
2
239.30534
308.34749
Finished
-
gaochenxiao
25d 18h 45m 38s
-
numpy.float32
float32
torch.float32
1024
0.0001
-
0.2
0.0001
true
1024
1024
0.0001
false
["cuda:0","cuda:1"]
0.99
hopper
Hopper-Hop-v1
dmc
-
10
10
-
10
1000000
1000
dmc
2000
2
-5
5
1
50
2
1000
2
hop
-
0.005
lamda-rl
SAC-Online
5
-
361.29089
8.20835
Finished
-
gaochenxiao
25d 18h 45m 38s
-
numpy.float32
float32
torch.float32
1024
0.0001
-
0.2
0.0001
true
1024
1024
0.0001
false
["cuda:0","cuda:1"]
0.99
quadruped
Quadruped-Run-v1
dmc
-
10
10
-
10
1000000
1000
dmc
2000
2
-5
5
1
50
2
1000
2
run
-
0.005
lamda-rl
SAC-Online
5
-
925.36261
37.31234
Finished
-
gaochenxiao
25d 18h 43m 34s
-
numpy.float32
float32
torch.float32
1024
0.0001
-
0.2
0.0001
true
1024
1024
0.0001
false
["cuda:0","cuda:1"]
0.99
walker
Walker-Run-v1
dmc
-
10
10
-
10
1000000
1000
dmc
2000
2
-5
5
1
50
2
1000
2
run
-
0.005
lamda-rl
SAC-Online
5
-
859.34398
14.34574
Finished
-
gaochenxiao
25d 18h 44m 44s
-
numpy.float32
float32
torch.float32
1024
0.0001
-
0.2
0.0001
true
1024
1024
0.0001
false
["cuda:0","cuda:1"]
0.99
cheetah
Cheetah-Run-v1
dmc
-
10
10
-
10
1000000
1000
dmc
2000
2
-5
5
1
50
2
1000
2
run
-
0.005
lamda-rl
SAC-Online
5
-
759.84143
15.01592
Finished
-
gaochenxiao
1m 40s
-
numpy.float32
float32
torch.float32
256
0.0003
-
0.2
0.0003
true
256
256
0.0003
false
cuda:1
0.99
-
Humanoid-v3
mujoco
-
10
10
-
10
1000000
1000
mujoco
3000
2
-20
5
1
50
2
1000
1
Humanoid-v3
-
0.005
lamda-rl
SAC-Online
2
-
6044.04935
1564.40543
Finished
-
gaochenxiao
3m 23s
-
numpy.float32
float32
torch.float32
256
0.0003
-
0.2
0.0003
true
256
256
0.0003
false
cuda:1
0.99
-
Swimmer-v3
mujoco
-
10
10
-
10
1000000
1000
mujoco
3000
2
-20
5
1
50
2
1000
1
Swimmer-v3
-
0.005
lamda-rl
SAC-Online
2
-
84.25445
8.22683
Finished
-
gaochenxiao
4m 36s
-
numpy.float32
float32
torch.float32
256
0.0003
-
0.2
0.0003
true
256
256
0.0003
false
cuda:1
0.99
-
Ant-v3
mujoco
-
10
10
-
10
1000000
1000
mujoco
3000
2
-20
5
1
50
2
1000
1
Ant-v3
-
0.005
lamda-rl
SAC-Online
2
-
6576.12182
760.00652
Finished
-
gaochenxiao
3m 55s
-
numpy.float32
float32
torch.float32
256
0.0003
-
0.2
0.0003
true
256
256
0.0003
false
cuda:1
0.99
-
Hopper-v3
mujoco
-
10
10
-
10
1000000
1000
mujoco
3000
2
-20
5
1
50
2
1000
1
Hopper-v3
-
0.005
lamda-rl
SAC-Online
2
-
2607.81245
598.49033
Finished
-
gaochenxiao
2m 17s
-
numpy.float32
float32
torch.float32
256
0.0003
-
0.2
0.0003
true
256
256
0.0003
false
cuda:1
0.99
-
HalfCheetah-v3
mujoco
-
10
10
-
10
1000000
1000
mujoco
3000
2
-20
5
1
50
2
1000
1
HalfCheetah-v3
-
0.005
lamda-rl
SAC-Online
2
-
15209.99521
31.54442
Finished
-
gaochenxiao
3m 41s
-
numpy.float32
float32
torch.float32
256
0.0003
-
0.2
0.0003
true
256
256
0.0003
false
cuda:1
0.99
-
Walker2d-v3
mujoco
-
10
10
-
10
1000000
1000
mujoco
3000
2
-20
5
1
50
2
1000
1
Walker2d-v3
-
0.005
lamda-rl
SAC-Online
2
-
5285.60873
245.10703
1-11
of 11