Claude_formanek's workspace
Runs
1,307
Name
132 visualized
system: maddpg+cql
system: maddpg+cql
3
44
system: omar
system: omar
3
45
system: iddpg+cql
system: iddpg+cql
3
44
system: maddpg
system: maddpg
3
44
State
Notes
User
Tags
Created
Runtime
Sweep
backend
dataset
env
scenario
seed
system
trainer_steps
Critic Loss
Loss
Mean Chosen Q-values
Mean Q-values
Policy Loss
Time for Train Step
Time to Sample
Train Steps Per Second
Trainer Steps
Trainer Steps (eval)
evaluator/episode_return
CQL Loss
Mean Critic Loss
Finished
-
claude_formanek
11d 17h 25m 54s
-
tf2
["Good","Medium","Poor"]
mamujoco
["2ant","2halfcheetah","4ant"]
3
maddpg+cql
-
-
-
-
358.95965
-354.21321
11.02638
0.0020429
0.098681
49999
50000
1453.7779
-
2249.10846
Finished
-
claude_formanek
7d 4h 31m 1s
-
tf2
["Good","Medium","Poor"]
mamujoco
["2ant","2halfcheetah","4ant"]
3
omar
-
-
-
-
195.56789
-58.7795
4.77534
0.0016863
0.21743
49999
50000
294.82413
3.01633
81.18197
Finished
-
claude_formanek
7d 5h 47m 45s
-
tf2
["Good","Medium","Poor"]
mamujoco
["2ant","2halfcheetah","4ant"]
3
iddpg+cql
-
-
-
-
170.34416
-168.9554
4.60472
0.0018241
0.22452
49999
50000
434.96344
2.64728
68.95215
Finished
-
claude_formanek
4d 23h 41m 53s
-
tf2
["Good","Medium","Poor"]
mamujoco
["2ant","2halfcheetah","4ant"]
3
maddpg
-
-
-
-
206967231.86582
-202963790.18247
0.45211
0.0012583
2.28597
49997.09091
50000
-2137.32863
-
4468295285910408
1-4
of 4