Skip to main content

Stopping Iters

Created on January 27|Last edited on January 27

Section 1




Select runs that logged debug/pg_stop_iter
to visualize data in this line chart.
Run set
0
Name
0 visualized
State
Notes
User
Tags
Created
Runtime
alpha
autotune
batch_size
buffer_size
cuda
episode_length
exp_name
gamma
gym_id
learning_rate
max_grad_norm
notb
policy_hid_sizes
prod_mode
q_hid_sizes
seed
target_network_frequency
target_update_interval
tau
torch_deterministic
total_timesteps
value_hid_sizes
wandb_entity
wandb_project_name
capture_video
ent_coef
milestone
vf_coef
clip_coef
end_e
exploration_fraction
start_e
update_epochs
policy_lr
target_kl
value_lr
lam
action_noise
actor_buffer_size
alpha_lr
anneal_lr
aux_batch_size
aux_minibatch_size
beta_clone
bias_init
Finished
-
dosssman
19h 43m 54s
-
-
100
-
true
-
bcq_cstm_loader_thrandint
0.99
Hopper-v2
-
0.5
-
-
true
-
1
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
15h 47m 49s
-
-
100
-
true
-
bcq_cstm_loader_thrandint
0.99
Hopper-v2
-
0.5
-
-
true
-
2
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
20h 5m 29s
-
-
100
-
true
-
bcq_cstm_loader_thrandint
0.99
Hopper-v2
-
0.5
-
-
true
-
2
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
16h 21m 12s
-
-
100
-
true
-
bcq_cstm_loader_thrandint
0.99
Hopper-v2
-
0.5
-
-
true
-
1
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
13h 21m 39s
-
-
100
-
true
-
bcq_cstm_loader_randint
0.99
Hopper-v2
-
0.5
-
-
true
-
5
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
13h 57m 57s
-
-
100
-
true
-
bcq_cstm_loader_randint
0.99
Hopper-v2
-
0.5
-
-
true
-
4
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
14h 35m 42s
-
-
100
-
true
-
bcq_cstm_loader_randint
0.99
Hopper-v2
-
0.5
-
-
true
-
8
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
13h 38m 54s
-
-
100
-
true
-
bcq_cstm_loader_randint
0.99
Hopper-v2
-
0.5
-
-
true
-
6
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
13h 45m 31s
-
-
100
-
true
-
bcq_cstm_loader_randint
0.99
Hopper-v2
-
0.5
-
-
true
-
3
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
14h 5m 43s
-
-
100
-
true
-
bcq_cstm_loader_randint
0.99
Hopper-v2
-
0.5
-
-
true
-
9
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
13h 56m 17s
-
-
100
-
true
-
bcq_cstm_loader_randint
0.99
Hopper-v2
-
0.5
-
-
true
-
10
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
13h 54m 26s
-
-
100
-
true
-
bcq_cstm_loader_randint
0.99
Hopper-v2
-
0.5
-
-
true
-
7
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
6h 18m 33s
-
-
100
-
true
-
bcq_cstm_loader_randint
0.99
Hopper-v2
-
0.5
-
-
true
-
1
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
6h 52m 11s
-
-
100
-
true
-
bcq_cstm_loader_randint
0.99
Hopper-v2
-
0.5
-
-
true
-
2
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Crashed
-
dosssman
9h 53m 55s
-
-
100
-
true
-
bcq_cstm_loader
0.99
Hopper-v2
-
0.5
-
-
true
-
10
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Crashed
-
dosssman
9h 54m 12s
-
-
100
-
true
-
bcq_cstm_loader
0.99
Hopper-v2
-
0.5
-
-
true
-
3
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Crashed
-
dosssman
9h 54m 6s
-
-
100
-
true
-
bcq_cstm_loader
0.99
Hopper-v2
-
0.5
-
-
true
-
7
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Failed
-
dosssman
9h 55m 18s
-
-
100
-
true
-
bcq_cstm_loader
0.99
Hopper-v2
-
0.5
-
-
true
-
4
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Crashed
-
dosssman
9h 54m 27s
-
-
100
-
true
-
bcq_cstm_loader
0.99
Hopper-v2
-
0.5
-
-
true
-
9
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Crashed
-
dosssman
9h 53m 50s
-
-
100
-
true
-
bcq_cstm_loader
0.99
Hopper-v2
-
0.5
-
-
true
-
5
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Crashed
-
dosssman
9h 54m 14s
-
-
100
-
true
-
bcq_cstm_loader
0.99
Hopper-v2
-
0.5
-
-
true
-
8
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Crashed
-
dosssman
9h 54m 36s
-
-
100
-
true
-
bcq_cstm_loader
0.99
Hopper-v2
-
0.5
-
-
true
-
6
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
1d 59m 39s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
3
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
1d 1h 5m 35s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
6
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
1d 1h 26m 38s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
4
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
1d 1h 24m 24s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
7
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
1d 1h 14m 43s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
10
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
1d 1h 5m 23s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
8
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
1d 1h 8m 52s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
5
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
1d 1h 6m 10s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
9
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
19h 46m 50s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
8
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
18h 35m 39s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
7
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
18h 48m 4s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
6
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
17h 17m 11s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
3
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
18h 13m 47s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
9
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
19h 17m 20s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
10
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
17h 43m 3s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
5
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
19h 28m 57s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
4
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
19h 21s
-
-
100
-
true
-
bcq_cstm_loader
0.99
Hopper-v2
-
0.5
-
-
true
-
2
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
18h 23m 55s
-
-
100
-
true
-
bcq_cstm_loader
0.99
Hopper-v2
-
0.5
-
-
true
-
1
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
15h 15m 19s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
2
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
15h 31m 35s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
1
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
20h 38m 7s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
1
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
20h 8m 45s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
2
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
Extremely lucky run ?
dosssman
11h 37m 50s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
2
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
Extremely lucky run ?
dosssman
11h 47m 48s
-
-
100
-
true
-
bcq
0.99
Hopper-v2
-
0.5
-
-
true
-
1
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
14h 35m 28s
-
-
100
-
true
-
bcq
0.99
hopper-bullet-medium-v0
-
0.5
-
-
true
-
8
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
13h 3m 34s
-
-
100
-
true
-
bcq
0.99
hopper-bullet-medium-v0
-
0.5
-
-
true
-
9
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
14h 15m 3s
-
-
100
-
true
-
bcq
0.99
hopper-bullet-medium-v0
-
0.5
-
-
true
-
5
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
Finished
-
dosssman
14h 33m 49s
-
-
100
-
true
-
bcq
0.99
hopper-bullet-medium-v0
-
0.5
-
-
true
-
6
1
-
0.005
true
1000000
-
cleanrl
cleanrl.benchmark
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
zeros
1-50
of 116