Gaochenxiao's workspace
Runs
135
Name
30 visualized
task: halfcheetah-medium-replay-v2
task: halfcheetah-medium-replay-v2
2
10
task: walker2d-medium-v2
task: walker2d-medium-v2
2
10
task: hopper-medium-expert-v2
task: hopper-medium-expert-v2
2
10
task: hopper-medium-v2
task: hopper-medium-v2
2
10
task: walker2d-medium-replay-v2
task: walker2d-medium-replay-v2
2
10
task: walker2d-medium-expert-v2
task: walker2d-medium-expert-v2
2
10
task: halfcheetah-medium-v2
task: halfcheetah-medium-v2
2
10
task: halfcheetah-medium-expert-v2
task: halfcheetah-medium-expert-v2
2
10
task: hopper-medium-replay-v2
task: hopper-medium-replay-v2
2
10
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
embedding_dim
encoder_lr
eval_episode
eval_interval
hidden_dim
lam
log_interval
max_action
max_buffer_size
max_epoch
max_trajectory_length
name
noise_clip
normalize_obs
normalize_reward
policy_noise
save_interval
seed
step_per_epoch
target_update_interval
task
use_checkpoint
wandb.entity
wandb.project
use_lap_buffer
Eval/length_mean
Eval/length_std
Eval/normalized_score_mean
Eval/normalized_score_std
loss/actor_loss
loss/bc_loss
loss/critic_loss
loss/encoder_loss
misc/max_q_uptodate
Finished
-
gaochenxiao
2d 20h 35m 7s
-
numpy.float32
float32
torch.float32
0.0003
2
256
0.0003
false
["cuda:0","cuda:1"]
0.99
256
0.0003
10
10
256
0.1
10
1
2000000
1000
1000
["d4rl","no_lap_buffer"]
0.5
false
false
0.2
50
2
1000
250
halfcheetah-medium-replay-v2
false
lamda-rl
TD7-D4RL
false
1000
0
54.16751
0.53018
-440.34684
42.0905
3.95512
0.0098926
584.04999
Finished
-
gaochenxiao
2d 21h 17m 46s
-
numpy.float32
float32
torch.float32
0.0003
2
256
0.0003
false
["cuda:0","cuda:1"]
0.99
256
0.0003
10
10
256
0.1
10
1
2000000
1000
1000
["d4rl","no_lap_buffer"]
0.5
false
false
0.2
50
2
1000
250
walker2d-medium-v2
false
lamda-rl
TD7-D4RL
[false,true]
883.41
140.06504
86.25654
15.16696
-347.42647
14.57771
2.17913
0.0029617
477.68564
Finished
-
gaochenxiao
2d 21h 35m 50s
-
numpy.float32
float32
torch.float32
0.0003
2
256
0.0003
false
["cuda:0","cuda:1"]
0.99
256
0.0003
10
10
256
0.1
10
1
2000000
1000
1000
["d4rl","no_lap_buffer"]
0.5
false
false
0.2
50
2
1000
250
hopper-medium-expert-v2
false
lamda-rl
TD7-D4RL
[false,true]
953.37
73.49896
107.35259
8.05015
-307.69224
18.0527
1.14847
0.0020606
385.96519
Finished
-
gaochenxiao
2d 20h 41m 57s
-
numpy.float32
float32
torch.float32
0.0003
2
256
0.0003
false
["cuda:0","cuda:1"]
0.99
256
0.0003
10
10
256
0.1
10
1
2000000
1000
1000
["d4rl","no_lap_buffer"]
0.5
false
false
0.2
50
2
1000
250
hopper-medium-v2
false
lamda-rl
TD7-D4RL
[false,true]
705.46
155.56176
72.69358
15.99656
-251.75267
13.59376
1.05938
0.001596
330.62642
Finished
-
gaochenxiao
2d 21h 25m 10s
-
numpy.float32
float32
torch.float32
0.0003
2
256
0.0003
false
["cuda:0","cuda:1"]
0.99
256
0.0003
10
10
256
0.1
10
1
2000000
1000
1000
["d4rl","no_lap_buffer"]
0.5
false
false
0.2
50
2
1000
250
walker2d-medium-replay-v2
false
lamda-rl
TD7-D4RL
[false,true]
941.1
103.75966
88.26257
11.01364
-270.18166
36.17531
5.34096
0.0059915
454.86335
Finished
-
gaochenxiao
2d 21h 27m 36s
-
numpy.float32
float32
torch.float32
0.0003
2
256
0.0003
false
["cuda:0","cuda:1"]
0.99
256
0.0003
10
10
256
0.1
10
1
2000000
1000
1000
["d4rl","no_lap_buffer"]
0.5
false
false
0.2
50
2
1000
250
walker2d-medium-expert-v2
false
lamda-rl
TD7-D4RL
[false,true]
1000
0
111.96489
0.10709
-430.69108
17.43174
2.16776
0.0035189
538.8707
Finished
-
gaochenxiao
2d 20h 24m 54s
-
numpy.float32
float32
torch.float32
0.0003
2
256
0.0003
false
["cuda:0","cuda:1"]
0.99
256
0.0003
10
10
256
0.1
10
1
2000000
1000
1000
["d4rl","no_lap_buffer"]
0.5
false
false
0.2
50
2
1000
250
halfcheetah-medium-v2
false
lamda-rl
TD7-D4RL
false
1000
0
59.05449
0.5556
-571.5394
22.17892
3.91769
0.0063324
633.70074
Finished
-
gaochenxiao
2d 20h 40m 5s
-
numpy.float32
float32
torch.float32
0.0003
2
256
0.0003
false
["cuda:0","cuda:1"]
0.99
256
0.0003
10
10
256
0.1
10
1
2000000
1000
1000
["d4rl","no_lap_buffer"]
0.5
false
false
0.2
50
2
1000
250
halfcheetah-medium-expert-v2
false
lamda-rl
TD7-D4RL
[false,true]
1000
0
101.91223
7.57275
-937.44648
40.20329
9.32401
0.0078901
1217.30015
Finished
-
gaochenxiao
2d 21h 7m 39s
-
numpy.float32
float32
torch.float32
0.0003
2
256
0.0003
false
["cuda:0","cuda:1"]
0.99
256
0.0003
10
10
256
0.1
10
1
2000000
1000
1000
["d4rl","no_lap_buffer"]
0.5
false
false
0.2
50
2
1000
250
hopper-medium-replay-v2
false
lamda-rl
TD7-D4RL
[false,true]
793.75
104.97856
80.71159
10.91576
-205.00829
28.14463
2.64948
0.0019307
320.34498
1-9
of 9