File tree Expand file tree Collapse file tree 9 files changed +29
-29
lines changed Expand file tree Collapse file tree 9 files changed +29
-29
lines changed Original file line number Diff line number Diff line change 29
29
},
30
30
{
31
31
"cell_type" : " code" ,
32
- "execution_count" : 2 ,
32
+ "execution_count" : 1 ,
33
33
"metadata" : {},
34
34
"outputs" : [],
35
35
"source" : [
51
51
},
52
52
{
53
53
"cell_type" : " code" ,
54
- "execution_count" : 3 ,
54
+ "execution_count" : 2 ,
55
55
"metadata" : {},
56
56
"outputs" : [
57
57
{
58
58
"name" : " stdout" ,
59
59
"output_type" : " stream" ,
60
60
"text" : [
61
- " 0.5.2 \n "
61
+ " 0.5.3 \n "
62
62
]
63
63
}
64
64
],
Original file line number Diff line number Diff line change 27
27
},
28
28
{
29
29
"cell_type" : " code" ,
30
- "execution_count" : 2 ,
30
+ "execution_count" : 1 ,
31
31
"metadata" : {},
32
32
"outputs" : [],
33
33
"source" : [
48
48
},
49
49
{
50
50
"cell_type" : " code" ,
51
- "execution_count" : 3 ,
51
+ "execution_count" : 2 ,
52
52
"metadata" : {},
53
53
"outputs" : [
54
54
{
55
55
"name" : " stdout" ,
56
56
"output_type" : " stream" ,
57
57
"text" : [
58
- " 0.5.2 \n "
58
+ " 0.5.3 \n "
59
59
]
60
60
}
61
61
],
Original file line number Diff line number Diff line change 32
32
},
33
33
{
34
34
"cell_type" : " code" ,
35
- "execution_count" : 2 ,
35
+ "execution_count" : 1 ,
36
36
"metadata" : {},
37
37
"outputs" : [],
38
38
"source" : [
55
55
},
56
56
{
57
57
"cell_type" : " code" ,
58
- "execution_count" : 3 ,
58
+ "execution_count" : 2 ,
59
59
"metadata" : {},
60
60
"outputs" : [
61
61
{
62
62
"name" : " stdout" ,
63
63
"output_type" : " stream" ,
64
64
"text" : [
65
- " 0.5.2 \n "
65
+ " 0.5.3 \n "
66
66
]
67
67
}
68
68
],
Original file line number Diff line number Diff line change 59
59
"name" : " stdout" ,
60
60
"output_type" : " stream" ,
61
61
"text" : [
62
- " 0.5.2 \n "
62
+ " 0.5.3 \n "
63
63
]
64
64
}
65
65
],
287
287
"name" : " stderr" ,
288
288
"output_type" : " stream" ,
289
289
"text" : [
290
- " q-func learning: 100%|██████████| 200/200 [00:17 <00:00, 11.40it /s]\n " ,
291
- " policy learning: 100%|██████████| 200/200 [00:48 <00:00, 4.12it /s]\n "
290
+ " q-func learning: 100%|██████████| 200/200 [00:19 <00:00, 10.51it /s]\n " ,
291
+ " policy learning: 100%|██████████| 200/200 [00:47 <00:00, 4.23it /s]\n "
292
292
]
293
293
}
294
294
],
324
324
"name" : " stderr" ,
325
325
"output_type" : " stream" ,
326
326
"text" : [
327
- " policy learning: 100%|██████████| 200/200 [00:40 <00:00, 4.88it /s]\n "
327
+ " policy learning: 100%|██████████| 200/200 [00:52 <00:00, 3.79it /s]\n "
328
328
]
329
329
}
330
330
],
361
361
"name" : " stderr" ,
362
362
"output_type" : " stream" ,
363
363
"text" : [
364
- " q-func learning: 100%|██████████| 200/200 [00:16 <00:00, 11.78it /s]\n " ,
365
- " policy learning: 100%|██████████| 200/200 [00:47 <00:00, 4.20it /s]\n "
364
+ " q-func learning: 100%|██████████| 200/200 [00:20 <00:00, 9.80it /s]\n " ,
365
+ " policy learning: 100%|██████████| 200/200 [00:54 <00:00, 3.64it /s]\n "
366
366
]
367
367
}
368
368
],
Original file line number Diff line number Diff line change 29
29
},
30
30
{
31
31
"cell_type" : " code" ,
32
- "execution_count" : 2 ,
32
+ "execution_count" : 1 ,
33
33
"metadata" : {},
34
34
"outputs" : [],
35
35
"source" : [
55
55
},
56
56
{
57
57
"cell_type" : " code" ,
58
- "execution_count" : 3 ,
58
+ "execution_count" : 2 ,
59
59
"metadata" : {},
60
60
"outputs" : [
61
61
{
62
62
"name" : " stdout" ,
63
63
"output_type" : " stream" ,
64
64
"text" : [
65
- " 0.5.2 \n "
65
+ " 0.5.3 \n "
66
66
]
67
67
}
68
68
],
Original file line number Diff line number Diff line change 29
29
},
30
30
{
31
31
"cell_type" : " code" ,
32
- "execution_count" : 2 ,
32
+ "execution_count" : 1 ,
33
33
"metadata" : {},
34
34
"outputs" : [],
35
35
"source" : [
47
47
},
48
48
{
49
49
"cell_type" : " code" ,
50
- "execution_count" : 3 ,
50
+ "execution_count" : 2 ,
51
51
"metadata" : {},
52
52
"outputs" : [],
53
53
"source" : [
57
57
},
58
58
{
59
59
"cell_type" : " code" ,
60
- "execution_count" : 4 ,
60
+ "execution_count" : 3 ,
61
61
"metadata" : {},
62
62
"outputs" : [],
63
63
"source" : [
67
67
},
68
68
{
69
69
"cell_type" : " code" ,
70
- "execution_count" : 5 ,
70
+ "execution_count" : 4 ,
71
71
"metadata" : {},
72
72
"outputs" : [
73
73
{
74
74
"name" : " stdout" ,
75
75
"output_type" : " stream" ,
76
76
"text" : [
77
- " 0.5.2 \n "
77
+ " 0.5.3 \n "
78
78
]
79
79
}
80
80
],
85
85
},
86
86
{
87
87
"cell_type" : " code" ,
88
- "execution_count" : 6 ,
88
+ "execution_count" : 5 ,
89
89
"metadata" : {},
90
90
"outputs" : [],
91
91
"source" : [
Original file line number Diff line number Diff line change @@ -743,7 +743,7 @@ class NNPolicyLearner(BaseOfflinePolicyLearner):
743
743
solver : str = "adam"
744
744
alpha : float = 0.0001
745
745
batch_size : Union [int , str ] = "auto"
746
- learning_rate_init : float = 0.001
746
+ learning_rate_init : float = 0.0001
747
747
max_iter : int = 200
748
748
shuffle : bool = True
749
749
random_state : Optional [int ] = None
@@ -1473,7 +1473,7 @@ class QFuncEstimator:
1473
1473
solver : str = "adam"
1474
1474
alpha : float = 0.0001
1475
1475
batch_size : Union [int , str ] = "auto"
1476
- learning_rate_init : float = 0.001
1476
+ learning_rate_init : float = 0.0001
1477
1477
max_iter : int = 200
1478
1478
shuffle : bool = True
1479
1479
random_state : Optional [int ] = None
Original file line number Diff line number Diff line change @@ -157,7 +157,7 @@ class ContinuousNNPolicyLearner(BaseContinuousOfflinePolicyLearner):
157
157
solver : str = "adam"
158
158
alpha : float = 0.0001
159
159
batch_size : Union [int , str ] = "auto"
160
- learning_rate_init : float = 0.001
160
+ learning_rate_init : float = 0.0001
161
161
max_iter : int = 100
162
162
shuffle : bool = True
163
163
random_state : Optional [int ] = None
@@ -732,7 +732,7 @@ class QFuncEstimatorForContinuousAction:
732
732
solver : str = "adam"
733
733
alpha : float = 0.0001
734
734
batch_size : Union [int , str ] = "auto"
735
- learning_rate_init : float = 0.001
735
+ learning_rate_init : float = 0.0001
736
736
max_iter : int = 100
737
737
shuffle : bool = True
738
738
random_state : Optional [int ] = None
Original file line number Diff line number Diff line change 1
- __version__ = "0.5.2 "
1
+ __version__ = "0.5.3 "
You can’t perform that action at this time.
0 commit comments