Caomingjun's workspace
Runs
965
Name
55 visualized
task: Reacher-v5
task: Reacher-v5
5
task: Swimmer-v5
task: Swimmer-v5
5
task: Hopper-v5
task: Hopper-v5
5
task: InvertedDoublePendulum-v5
task: InvertedDoublePendulum-v5
5
task: HumanoidStandup-v5
task: HumanoidStandup-v5
5
task: HalfCheetah-v5
task: HalfCheetah-v5
5
task: Pusher-v5
task: Pusher-v5
5
task: Ant-v5
task: Ant-v5
5
task: Walker2d-v5
task: Walker2d-v5
5
task: Humanoid-v5
task: Humanoid-v5
5
task: InvertedPendulum-v5
task: InvertedPendulum-v5
5
State
Notes
User
Tags
Created
Runtime
Sweep
algo.actor_hidden_dims
algo.actor_lr
algo.beta
algo.conditional_logstd
algo.critic_ensemble_size
algo.critic_hidden_dims
algo.critic_lr
algo.deterministic_actor
algo.discount
algo.expectile
algo.layer_norm
algo.lr_decay_steps
algo.max_action
algo.min_action
algo.name
algo.opt_decay_schedule
algo.policy_logstd_min
algo.tau
algo.value_hidden_dims
algo.value_lr
data.batch_size
data.clip_eps
data.dataset
data.norm_reward
data.scan
device
eval.interval
eval.num_episodes
eval.num_samples
eval.stats_interval
eval.temperature
log.dir
log.entity
log.interval
log.project
log.save_ckpt
log.save_video
log.tag
mode
norm_obs
pretrain_steps
seed
task
train_steps
Finished
-
gaochenxiao
3m 18s
-
256
0.0003
-
-
2
256
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
["0","1","5","7"]
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
2
Reacher-v5
-
Finished
-
gaochenxiao
3m 13s
-
256
0.0003
-
-
2
256
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
["2","3","4"]
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
2
Swimmer-v5
-
Finished
-
gaochenxiao
3m 25s
-
256
0.0003
-
-
2
256
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
["3","4","5","6","7"]
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
2
Hopper-v5
-
Finished
-
gaochenxiao
3m 22s
-
256
0.0003
-
-
2
256
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
["0","1","3","5","6"]
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
2
InvertedDoublePendulum-v5
-
Finished
-
gaochenxiao
3m 34s
-
256
0.0003
-
-
2
256
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
["0","1","2","3","4"]
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
2
HumanoidStandup-v5
-
Finished
-
gaochenxiao
3m 21s
-
256
0.0003
-
-
2
256
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
["0","1","2","6","7"]
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
2
HalfCheetah-v5
-
Finished
-
gaochenxiao
36s
-
[256,256]
0.0003
-
-
2
[256,256]
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
0
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
2
HalfCheetah-v5
-
Finished
-
gaochenxiao
39s
-
[256,256]
0.0003
-
-
2
[256,256]
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
7
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
1
HalfCheetah-v5
-
Finished
-
gaochenxiao
36s
-
[256,256]
0.0003
-
-
2
[256,256]
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
1
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
3
HalfCheetah-v5
-
Finished
-
gaochenxiao
38s
-
[256,256]
0.0003
-
-
2
[256,256]
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
2
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
4
HalfCheetah-v5
-
Finished
-
gaochenxiao
37s
-
[256,256]
0.0003
-
-
2
[256,256]
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
6
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
0
HalfCheetah-v5
-
Finished
-
gaochenxiao
3m 24s
-
256
0.0003
-
-
2
256
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
["2","3","4","5","6"]
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
2
Pusher-v5
-
Finished
-
gaochenxiao
3m 28s
-
256
0.0003
-
-
2
256
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
["1","2","3","4","5"]
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
2
Ant-v5
-
Finished
-
gaochenxiao
3m 7s
-
256
0.0003
-
-
2
256
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
["1","5","6","7"]
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
2
Walker2d-v5
-
Finished
-
gaochenxiao
34s
-
[256,256]
0.0003
-
-
2
[256,256]
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
6
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
0
Walker2d-v5
-
Finished
-
gaochenxiao
35s
-
[256,256]
0.0003
-
-
2
[256,256]
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
1
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
2
Walker2d-v5
-
Finished
-
gaochenxiao
35s
-
[256,256]
0.0003
-
-
2
[256,256]
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
6
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
4
Walker2d-v5
-
Finished
-
gaochenxiao
35s
-
[256,256]
0.0003
-
-
2
[256,256]
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
5
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
3
Walker2d-v5
-
Finished
-
gaochenxiao
32s
-
[256,256]
0.0003
-
-
2
[256,256]
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
7
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
1
Walker2d-v5
-
Finished
-
gaochenxiao
3m 32s
-
256
0.0003
-
-
2
256
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
["0","4","5","6","7"]
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
2
Humanoid-v5
-
Finished
-
gaochenxiao
3m 18s
-
256
0.0003
-
-
2
256
0.0003
-
0.99
-
false
-
-
-
sac
-
-
-
-
-
-
-
-
-
-
["1","2","6","7"]
-
10
1
-
-
logs
lamda-rl
-
flow-rl
false
false
default
-
false
-
2
InvertedPendulum-v5
-
1-11
of 11