Yuanmingqi's workspace
Runs
1,708
Name
20 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
GAE coefficient
LSTM
action entropy coefficient
agent learning rate
backbone
batch size
beta
discount factor
env
environment steps
environments per worker
episode steps
epochs per rollout
intrinsic reward
irs learning rate
kappa
latent_dim
max gradient norm
number of workers
observation normalization
optimizer
reward forward filter
reward normalization
seed
update proportion
value clip range
value loss coefficient
weight initialization
Disagreement/episode_reward
E3B/episode_reward
ICM/episode_reward
NGU/episode_reward
PseudoCounts/episode_reward
RE3/episode_reward
RIDE/episode_reward
RND/episode_reward
Extrinsic/episode_reward
Finished
-
yuanmingqi
8m 50s
-
0.95
false
0.01
0.0005
PPO
2048
1
0.999
Procgen-MazeHard-v0 (num_levels=1)
25000000
64
256
3
["Disagreement","E3B","Extrinsic","ICM","NGU","PseudoCounts","RE3","RIDE","RND"]
0.001
0
128
0.5
1
["Min-Max","RMS"]
Adam
false
["Min-Max","RMS","Vanilla"]
3
["0.1","0.5","1.0"]
0.2
0.5
orthogonal
1
0
0
3
2
5
2
1
0
Finished
-
yuanmingqi
14m 12s
-
0.95
false
0.01
0.0005
PPO
2048
1
0.999
Procgen-MazeHard-v0 (num_levels=200)
25000000
64
256
3
["Disagreement","E3B","Extrinsic","ICM","NGU","PseudoCounts","RE3","RIDE","RND"]
0.001
0
128
0.5
1
["Min-Max","RMS"]
Adam
false
["Min-Max","RMS","Vanilla"]
3
["0.1","0.5","1.0"]
0.2
0.5
orthogonal
4.1
3.7
5.2
3.9
5.4
5.3
4.3
4.7
4.6
Finished
-
yuanmingqi
31s
-
0.95
false
0.01
0.00025
PPO
1024
0.25
0.99
MiniGrid-MultiRoom-N10-S10-v0
10000000
256
32
4
["E3B","ICM","NGU","RE3"]
0.001
0
128
0.5
1
Min-Max
Adam
false
RMS
2.83333
1.0
0.1
0.5
orthogonal
-
60.46
0
61.624
-
57.804
-
-
-
Finished
-
yuanmingqi
30s
-
0.95
false
0.01
0.00025
PPO
1024
0.25
0.99
MiniGrid-Dynamic-Obstacles-16x16-v0
10000000
256
32
4
["E3B","ICM","NGU","RE3"]
0.001
0
128
0.5
1
Min-Max
Adam
false
RMS
3
1.0
0.1
0.5
orthogonal
-
57.77813
0
19.41992
-
15.43926
-
-
-
Finished
-
yuanmingqi
29s
-
0.95
false
0.01
0.00025
PPO
1024
0.25
0.99
MiniGrid-LockedRoom-v0
10000000
256
32
4
["E3B","ICM","NGU","RE3"]
0.001
0
128
0.5
1
Min-Max
Adam
false
RMS
3
1.0
0.1
0.5
orthogonal
-
45.27789
65.08842
30.93895
-
53.71895
-
-
-
Finished
-
yuanmingqi
31s
-
0.95
false
0.01
0.00025
PPO
1024
0.25
0.99
MiniGrid-MultiRoom-N12-S10-v0
10000000
256
32
4
["E3B","ICM","NGU","RE3"]
0.001
0
128
0.5
1
Min-Max
Adam
false
RMS
3
1.0
0.1
0.5
orthogonal
-
60.905
0
63.0925
-
63.5275
-
-
-
Finished
-
yuanmingqi
23s
-
0.95
false
0.01
0.00025
PPO
1024
0.25
0.99
MiniGrid-MultiRoom-N7-S8-v0
10000000
256
32
4
["E3B","ICM","NGU","RE3"]
0.001
0
128
0.5
1
Min-Max
Adam
false
RMS
3
1.0
0.1
0.5
orthogonal
-
65.33714
0
66.03143
-
64.50143
-
-
-
Finished
-
yuanmingqi
21s
-
0.95
false
0.01
0.00025
PPO
1024
0.25
0.99
MiniGrid-KeyCorridorS10R7-v0
10000000
256
32
4
["E3B","ICM","NGU","RE3"]
0.001
0
128
0.5
1
Min-Max
Adam
false
RMS
3
1.0
0.1
0.5
orthogonal
-
3.2056
0
7.5852
-
16.8856
-
-
-
Finished
-
yuanmingqi
20s
-
0.95
false
0.01
0.00025
PPO
1024
0.25
0.99
MiniGrid-KeyCorridorS9R6-v0
10000000
256
32
4
["E3B","ICM","NGU","RE3"]
0.001
0
128
0.5
1
Min-Max
Adam
false
RMS
3
1.0
0.1
0.5
orthogonal
-
6.16963
0
12.58815
-
23.33185
-
-
-
Finished
-
yuanmingqi
17s
-
0.95
false
0.01
0.00025
PPO
1024
0.25
0.99
MiniGrid-KeyCorridorS8R5-v0
10000000
256
32
4
["E3B","ICM","NGU","RE3"]
0.001
0
128
0.5
1
Min-Max
Adam
false
RMS
3
1.0
0.1
0.5
orthogonal
-
8.84344
0
8.44875
-
42.61
-
-
-
Finished
-
yuanmingqi
14m 27s
-
0.95
false
0.01
0.00025
PPO
1024
0.25
0.99
MiniGrid-DoorKey-16x16-v0
10000000
256
32
4
["Disagreement","E3B","ICM","NGU","PseudoCounts","RE3","RIDE","RND"]
0.001
0
128
0.5
1
["Min-Max","RMS"]
Adam
false
["Min-Max","RMS","Vanilla"]
5.5
["0.01","0.1","0.5","1.0"]
0.1
0.5
orthogonal
79.75717
66.65776
0.68117
40.1023
33.82496
75.19001
7.09096
7.91472
-
Finished
-
yuanmingqi
20m 10s
-
0.95
false
0.01
0.00025
PPO
256
1
0.99
SuperMarioBros-1-1-v3
10000000
8
128
4
["Disagreement","E3B","ICM","NGU","PseudoCounts","RE3","RIDE","RND"]
0.001
0
128
0.5
1
["Min-Max","RMS"]
Adam
false
["Min-Max","RMS","Vanilla"]
5.5
["0.01","0.1","0.5","1.0"]
0.1
0.5
orthogonal
9.722
25.55202
9.24526
14.838
17.90329
12.36968
21.16553
9.39249
-
1-12
of 12