Luthier-man's workspace
Runs
815
Name
60 visualized
model: C-DQN-PER-Rank
model: C-DQN-PER-Rank
10
model: Q-DQN-PER-Prop
model: Q-DQN-PER-Prop
10
model: C-DQN
model: C-DQN
10
model: C-DQN-PER-Prop
model: C-DQN-PER-Prop
10
model: Q-DQN
model: Q-DQN
10
model: Q-DQN-PER-Rank
model: Q-DQN-PER-Rank
10
State
Notes
User
Tags
Created
Runtime
Sweep
PER_Alpha
PER_Beta
PER_Beta_increment
PER_e
batch_size
buffer_size
env
epsilon
epsilon_decay
epsilon_min
gamma
is_DDQN
is_Reupload
is_constrained
is_constrained_angle
is_constrained_x
is_quantum
is_ranking
learning_rate
learning_rate_in
learning_rate_out
loss
max_steps
model
n_episodes
n_layers
num_episodes
pre_fill
seed
train_start
update_model
update_target
use_PER
Average Loss Per Episode
Average Q-values
Beta
Episode Time
Epsilon
Running Average Rewards (50)
Test Episode
Total Average Test Reward
Total Average Testing Reward
Total Average Training Reward
Total Test Rewards
Finished
-
luthier-man
2h 26m 44s
-
0.6
0.4
0
0.00001
64
10000
CartPole-v1
1
0.995
0.01
0.95
false
false
-
-
-
false
true
0.001
0.01
0.1
MSELoss()
-
C-DQN-PER-Rank
200
2
-
false
4.5
-
-
1
true
0.080434
19.90082
1
-
0.01
182.508
199
167.35
-
176.5995
193.7
Finished
-
luthier-man
14h 16m 14s
-
0.6
0.4
0
0.00001
64
10000
CartPole-v1
1
0.995
0.01
0.95
false
true
-
-
-
true
false
0.001
0.01
0.1
MSELoss()
-
Q-DQN-PER-Prop
200
2
-
false
4.5
-
-
1
true
0.0018221
17.57425
1
-
0.01
236.94
199
317.3395
-
218.9125
317
Finished
-
luthier-man
1h 50m 4s
-
0.6
0.4
0
0.00001
64
10000
CartPole-v1
1
0.995
0.01
0.95
false
false
-
-
-
false
false
0.001
0.01
0.1
MSELoss()
-
C-DQN
200
2
-
false
4.5
-
-
1
false
0.16974
19.02909
0
-
0.01
178.814
199
166.549
-
167.273
144
Finished
-
luthier-man
2h 5m 13s
-
0.6
0.4
0
0.00001
64
10000
CartPole-v1
1
0.995
0.01
0.95
false
false
-
-
-
false
false
0.001
0.01
0.1
MSELoss()
-
C-DQN-PER-Prop
200
2
-
false
4.5
-
-
1
true
0.0012845
18.28578
1
-
0.01
209.726
199
190.8595
-
166.085
215.1
Finished
-
luthier-man
13h 50m 16s
-
0.6
0.4
0
0.00001
64
10000
CartPole-v1
1
0.995
0.01
0.95
false
true
-
-
-
true
false
0.001
0.01
0.1
MSELoss()
-
Q-DQN
200
2
-
false
4.5
-
-
1
false
0.31875
18.86483
0
-
0.01
220.116
199
260.8975
-
224.3155
276.5
Finished
-
luthier-man
14h 57m 36s
-
0.6
0.4
0
0.00001
64
10000
CartPole-v1
1
0.995
0.01
0.95
false
true
-
-
-
true
true
0.001
0.01
0.1
MSELoss()
-
Q-DQN-PER-Rank
200
2
-
false
4.5
-
-
1
true
0.19052
19.86361
1
-
0.01
271.104
199
297.8065
-
238.8145
303.8
1-6
of 6