Lawmen-05-shark's workspace
Runs
24
Name
24 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
algo
collector.total_env_steps
collector.agent_steps_per_batch
collector.agent_steps_per_env
collector.is_episodic
collector.num_batches
collector.num_training_phases
collector.total_agent_steps
collector.total_env_steps
debug.benchmark_env
debug.check_env_specs
device.collector_storage
device.rollout
device.training
env.name
env
eval.agent_steps_per_eval
eval.log_level
eval.record_video
eval.total_agent_steps
eval.video_agent_fps
job_subdir
logging.log_level
logging.save_model_level
loss.policy.kwargs.clip_epsilon
loss.policy.kwargs.feature_trust_region_coef
loss.policy.advantage
loss.policy.kl_early_stop
loss.policy.kl_stop_limit
loss.policy.kwargs.beta_kl
loss.policy.kwargs.clip_epsilon
loss.policy.kwargs.entropy_coef
loss.policy.kwargs.feature_trust_all_layers
loss.policy.kwargs.feature_trust_region_coef
loss.policy.kwargs.feature_trust_region_limit
loss.policy.kwargs.feature_trust_region_regularize_or_clip
loss.policy.kwargs.feature_trust_region_type
loss.policy.kwargs.feature_trust_use_preactivation
loss.policy.kwargs.kl_target
loss.policy.kwargs.normalize_advantage
loss.policy.kwargs.safe_logratio
loss.policy.kwargs.use_clipped_loss
loss.policy.kwargs.use_episodic_mask
loss.policy.module
Finished
-
skandermoalla
experiment
rebuttal
shared-trunk
4h 19m 43s
-
ppo-clip
-
1024
128
false
32552
32552
33333248
99999744
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
3515616000
20
atari-ppo/sparse
0.1
2.5
-
-
advantage_actor
false
0.01
0
0.1
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
experiment
rebuttal
shared-trunk
4h 17m 46s
-
ppo-clip
-
1024
128
false
32552
32552
33333248
99999744
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
3515616000
20
atari-ppo/sparse
0.1
2.5
-
-
advantage_actor
false
0.01
0
0.1
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
experiment
rebuttal
shared-trunk
4h 19m 13s
-
ppo-clip
-
1024
128
false
32552
32552
33333248
99999744
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
3515616000
20
atari-ppo/sparse
0.1
2.5
-
-
advantage_actor
false
0.01
0
0.1
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
experiment
rebuttal
shared-trunk
4h 21m 18s
-
ppo-clip
-
1024
128
false
32552
32552
33333248
99999744
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
3515616000
20
atari-ppo/sparse
0.1
2.5
-
-
advantage_actor
false
0.01
0
0.1
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
experiment
rebuttal
shared-trunk
4h 20m 5s
-
ppo-clip
-
1024
128
false
32552
32552
33333248
99999744
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
3515616000
20
atari-ppo/sparse
0.1
2.5
-
-
advantage_actor
false
0.01
0
0.1
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
experiment
rebuttal
shared-trunk
4h 14m 12s
-
ppo-clip
-
1024
128
false
32552
32552
33333248
99999744
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
3515616000
20
atari-ppo/sparse
0.1
2.5
-
-
advantage_actor
false
0.01
0
0.1
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
baseline
experiment
rebuttal
8h 25m 7s
-
ppo-clip
200000000
1024
128
false
65104
65104
66666496
199999488
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
7031232000
20
atari-ppo/baselines
0.1
2.5
0.2
-
advantage_actor
false
0.01
0
0.2
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
baseline
experiment
rebuttal
8h 20m 4s
-
ppo-clip
200000000
1024
128
false
65104
65104
66666496
199999488
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
7031232000
20
atari-ppo/baselines
0.1
2.5
0.2
-
advantage_actor
false
0.01
0
0.2
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
baseline
experiment
rebuttal
8h 23m 33s
-
ppo-clip
200000000
1024
128
false
65104
65104
66666496
199999488
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
7031232000
20
atari-ppo/baselines
0.1
2.5
0.2
-
advantage_actor
false
0.01
0
0.2
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
baseline
experiment
rebuttal
8h 19m 49s
-
ppo-clip
200000000
1024
128
false
65104
65104
66666496
199999488
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
7031232000
20
atari-ppo/baselines
0.1
2.5
0.1
-
advantage_actor
false
0.01
0
0.1
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
baseline
experiment
rebuttal
8h 21m 6s
-
ppo-clip
200000000
1024
128
false
65104
65104
66666496
199999488
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
7031232000
20
atari-ppo/baselines
0.1
2.5
0.1
-
advantage_actor
false
0.01
0
0.1
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
baseline
experiment
rebuttal
8h 31m 46s
-
ppo-clip
200000000
1024
128
false
65104
65104
66666496
199999488
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
7031232000
20
atari-ppo/baselines
0.1
2.5
0.1
-
advantage_actor
false
0.01
0
0.1
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
baseline
experiment
rebuttal
8h 24m 54s
-
ppo-clip
200000000
1024
128
false
65104
65104
66666496
199999488
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
7031232000
20
atari-ppo/baselines
0.1
2.5
0.05
-
advantage_actor
false
0.01
0
0.05
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
baseline
experiment
rebuttal
8h 24m 23s
-
ppo-clip
200000000
1024
128
false
65104
65104
66666496
199999488
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
7031232000
20
atari-ppo/baselines
0.1
2.5
0.05
-
advantage_actor
false
0.01
0
0.05
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
baseline
experiment
rebuttal
8h 19m 18s
-
ppo-clip
200000000
1024
128
false
65104
65104
66666496
199999488
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
7031232000
20
atari-ppo/baselines
0.1
2.5
0.05
-
advantage_actor
false
0.01
0
0.05
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
baseline
experiment
rebuttal
8h 28m 49s
-
ppo-clip
200000000
1024
128
false
65104
65104
66666496
199999488
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
7031232000
20
atari-ppo/baselines
0.1
2.5
-
-
advantage_actor
false
0.01
0
0.1
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
baseline
experiment
rebuttal
8h 24m 36s
-
ppo-clip
200000000
1024
128
false
65104
65104
66666496
199999488
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
7031232000
20
atari-ppo/baselines
0.1
2.5
-
-
advantage_actor
false
0.01
0
0.1
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
baseline
experiment
rebuttal
8h 19m 34s
-
ppo-clip
200000000
1024
128
false
65104
65104
66666496
199999488
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
7031232000
20
atari-ppo/baselines
0.1
2.5
-
-
advantage_actor
false
0.01
0
0.1
0.01
false
0
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
control
experiment
rebuttal
regularize
8h 26m 2s
-
ppo-clip
200000000
1024
128
false
65104
65104
66666496
199999488
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
7031232000
20
atari-ppo/control/regularize
0.1
2.5
-
1
advantage_actor
false
0.01
0
0.1
0.01
false
1
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
Finished
-
skandermoalla
control
experiment
rebuttal
regularize
8h 22m 15s
-
ppo-clip
200000000
1024
128
false
65104
65104
66666496
199999488
false
false
cuda:0
cuda:0
cuda:0
ALE/Phoenix-v5
gym-atari
108000
101
true
7031232000
20
atari-ppo/control/regularize
0.1
2.5
-
1
advantage_actor
false
0.01
0
0.1
0.01
false
1
0.1
regularize
l2
true
0.01
true
false
true
false
PPOLoss
1-20
of 24