sumo43 commited on
Commit
e7f0a35
·
1 Parent(s): 5716bd6

Upload 24 files

Browse files
config.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:793ef203ff3df940ee5d97eaaede7f090a049f1d71fa2f04943a5bdab9fc7b81
3
+ size 667
dataset_stats.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42bd7e0bb79f414de130ece5bc452e2462d870318b0eb943874ad4b5afe6c415
3
+ size 23196
policy_best.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad14460b8849ac4252c1cbe772d2a86bfb212ca789e714eda02758b6f315fd1
3
+ size 336120057
policy_last.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad14460b8849ac4252c1cbe772d2a86bfb212ca789e714eda02758b6f315fd1
3
+ size 336120057
policy_step_0_seed_0.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af8f4af2fb60956ed9bc55665c5357a3aeab86d4ff91a5672b15ff5db3a372de
3
+ size 336123171
policy_step_1000_seed_0.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672eb3bd7a5912f433781ff8d8663f2da9d900d3223ba3d820dbc9642747102c
3
+ size 336124273
policy_step_1500_seed_0.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f01d8e2168eaea1073bd4a16b177f4b7d55d5a00594dc90861449c6da5e4aab8
3
+ size 336124273
policy_step_2000_seed_0.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9a64e02428d444f9918875f538903d915b61b6944fb9fe83744404bf5082725
3
+ size 336124273
policy_step_2500_seed_0.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a967ca7872debda50ac93d20d90664acfa920fe17a39ce7548d8294e6b4b804
3
+ size 336124273
policy_step_3000_seed_0.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aafae2b2aeb9c8abf05c87eb6e210d1edae894ba7663595cc47196bcdb1900bc
3
+ size 336124273
policy_step_3500_seed_0.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0e118d02a4eac69a534af92bd1c0a21624e9b260dd51cbd478b84579efcc03d
3
+ size 336124273
policy_step_4000_seed_0.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91439865e38e8a5034aa64a9adfddc8f6ba668c61869c6be1a80dd6f9de0064e
3
+ size 336124273
policy_step_4500_seed_0.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ba291907667d97d8c2bbe69fca09c820c2f03663d3dc93e2d42234d3e0c50a5
3
+ size 336124273
policy_step_500_seed_0.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21610f1cfef63a5c8366a2e9bbc6f3f85b6bc822f7c122c0c2a3418b5af0a61b
3
+ size 336123927
result_policy_last.txt ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ Success rate: 0.2
3
+ Average return: 135.2
4
+
5
+ Reward >= 0: 5/5 = 100.0%
6
+ Reward >= 1: 5/5 = 100.0%
7
+ Reward >= 2: 3/5 = 60.0%
8
+ Reward >= 3: 1/5 = 20.0%
9
+ Reward >= 4: 1/5 = 20.0%
10
+ [60, 489, 13, 112, 2]
11
+
12
+ [1, 4, 2, 1, 2]
result_policy_step_1000_seed_0.txt ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ Success rate: 0.0
3
+ Average return: 3.9
4
+
5
+ Reward >= 0: 10/10 = 100.0%
6
+ Reward >= 1: 3/10 = 30.0%
7
+ Reward >= 2: 2/10 = 20.0%
8
+ Reward >= 3: 0/10 = 0.0%
9
+ Reward >= 4: 0/10 = 0.0%
10
+ [0, 25, 0, 6, 0, 0, 0, 0, 0, 8]
11
+
12
+ [0, 2, 0, 2, 0, 0, 0, 0, 0, 1]
result_policy_step_1500_seed_0.txt ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ Success rate: 0.0
3
+ Average return: 22.0
4
+
5
+ Reward >= 0: 10/10 = 100.0%
6
+ Reward >= 1: 6/10 = 60.0%
7
+ Reward >= 2: 5/10 = 50.0%
8
+ Reward >= 3: 0/10 = 0.0%
9
+ Reward >= 4: 0/10 = 0.0%
10
+ [0, 29, 0, 10, 0, 56, 9, 1, 0, 115]
11
+
12
+ [0, 2, 0, 2, 0, 2, 2, 1, 0, 2]
result_policy_step_2000_seed_0.txt ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ Success rate: 0.0
3
+ Average return: 20.4
4
+
5
+ Reward >= 0: 10/10 = 100.0%
6
+ Reward >= 1: 6/10 = 60.0%
7
+ Reward >= 2: 6/10 = 60.0%
8
+ Reward >= 3: 0/10 = 0.0%
9
+ Reward >= 4: 0/10 = 0.0%
10
+ [0, 68, 2, 21, 0, 4, 33, 0, 0, 76]
11
+
12
+ [0, 2, 2, 2, 0, 2, 2, 0, 0, 2]
result_policy_step_2500_seed_0.txt ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ Success rate: 0.2
3
+ Average return: 109.8
4
+
5
+ Reward >= 0: 10/10 = 100.0%
6
+ Reward >= 1: 9/10 = 90.0%
7
+ Reward >= 2: 9/10 = 90.0%
8
+ Reward >= 3: 2/10 = 20.0%
9
+ Reward >= 4: 2/10 = 20.0%
10
+ [3, 497, 3, 61, 6, 67, 413, 13, 0, 35]
11
+
12
+ [2, 4, 2, 2, 2, 2, 4, 2, 0, 2]
result_policy_step_3000_seed_0.txt ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ Success rate: 0.2
3
+ Average return: 157.0
4
+
5
+ Reward >= 0: 10/10 = 100.0%
6
+ Reward >= 1: 9/10 = 90.0%
7
+ Reward >= 2: 9/10 = 90.0%
8
+ Reward >= 3: 2/10 = 20.0%
9
+ Reward >= 4: 2/10 = 20.0%
10
+ [6, 625, 5, 11, 3, 42, 51, 175, 0, 652]
11
+
12
+ [2, 4, 2, 2, 2, 2, 2, 2, 0, 4]
result_policy_step_3500_seed_0.txt ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ Success rate: 0.5
3
+ Average return: 333.1
4
+
5
+ Reward >= 0: 10/10 = 100.0%
6
+ Reward >= 1: 9/10 = 90.0%
7
+ Reward >= 2: 9/10 = 90.0%
8
+ Reward >= 3: 5/10 = 50.0%
9
+ Reward >= 4: 5/10 = 50.0%
10
+ [2, 628, 57, 644, 658, 55, 689, 572, 0, 26]
11
+
12
+ [2, 4, 2, 4, 4, 2, 4, 4, 0, 2]
result_policy_step_4000_seed_0.txt ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ Success rate: 0.1
3
+ Average return: 97.8
4
+
5
+ Reward >= 0: 10/10 = 100.0%
6
+ Reward >= 1: 9/10 = 90.0%
7
+ Reward >= 2: 6/10 = 60.0%
8
+ Reward >= 3: 1/10 = 10.0%
9
+ Reward >= 4: 1/10 = 10.0%
10
+ [17, 7, 44, 14, 0, 152, 25, 33, 98, 588]
11
+
12
+ [1, 1, 2, 2, 0, 2, 2, 2, 1, 4]
result_policy_step_4500_seed_0.txt ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ Success rate: 0.3
3
+ Average return: 208.9
4
+
5
+ Reward >= 0: 10/10 = 100.0%
6
+ Reward >= 1: 9/10 = 90.0%
7
+ Reward >= 2: 7/10 = 70.0%
8
+ Reward >= 3: 3/10 = 30.0%
9
+ Reward >= 4: 3/10 = 30.0%
10
+ [60, 489, 13, 112, 2, 28, 694, 34, 0, 657]
11
+
12
+ [1, 4, 2, 1, 2, 2, 4, 2, 0, 4]
result_policy_step_500_seed_0.txt ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ Success rate: 0.0
3
+ Average return: 1.1
4
+
5
+ Reward >= 0: 10/10 = 100.0%
6
+ Reward >= 1: 3/10 = 30.0%
7
+ Reward >= 2: 2/10 = 20.0%
8
+ Reward >= 3: 0/10 = 0.0%
9
+ Reward >= 4: 0/10 = 0.0%
10
+ [0, 0, 7, 0, 0, 2, 0, 0, 0, 2]
11
+
12
+ [0, 0, 2, 0, 0, 1, 0, 0, 0, 2]