Add level2_deformable_from_rigid (suite transfer: level2_deformable tasks from the final level2_rigid policy, 50k further steps; evaluation pending)
Browse files- multi_task/level2_deformable_from_rigid/lora_step_0010000.npz +3 -0
- multi_task/level2_deformable_from_rigid/lora_step_0020000.npz +3 -0
- multi_task/level2_deformable_from_rigid/lora_step_0030000.npz +3 -0
- multi_task/level2_deformable_from_rigid/lora_step_0040000.npz +3 -0
- multi_task/level2_deformable_from_rigid/lora_step_0050000.npz +3 -0
- multi_task/level2_deformable_from_rigid/metadata.json +245 -0
- multi_task/level2_deformable_from_rigid/norm_stats.json +376 -0
multi_task/level2_deformable_from_rigid/lora_step_0010000.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b59c5e3a39555e0fc9d2edb6e127ea5a763e21c6e5e4dc4183db56289ac0612f
|
| 3 |
+
size 1867943218
|
multi_task/level2_deformable_from_rigid/lora_step_0020000.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14a26b031de747f89f7298e5b8d5dc5d88127919e6e0d39a39b289f135229f4f
|
| 3 |
+
size 1867943218
|
multi_task/level2_deformable_from_rigid/lora_step_0030000.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92653f72cbb35bee686f300ca65b39ca4304c698c94a12594828a4bba9466242
|
| 3 |
+
size 1867943218
|
multi_task/level2_deformable_from_rigid/lora_step_0040000.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1571b7d1519a79dd9d4185ad2b8ac7f7689a774c9605fba51b4087d203e0524
|
| 3 |
+
size 1867943218
|
multi_task/level2_deformable_from_rigid/lora_step_0050000.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9665a5e298c5ff6ce7c05b97c45d97f524e32f6b6e76b6bd4d269bd78b0155a5
|
| 3 |
+
size 1867943218
|
multi_task/level2_deformable_from_rigid/metadata.json
ADDED
|
@@ -0,0 +1,245 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"suite": "level2_deformable_from_rigid",
|
| 3 |
+
"suite_id": "x_rigid2deform",
|
| 4 |
+
"description": "level2_deformable tasks, initialised from the final level2_rigid policy (suite transfer), 50k further steps",
|
| 5 |
+
"campaign": "pi05_lv2xfer_20261101",
|
| 6 |
+
"tasks": [
|
| 7 |
+
"FoldShirt-v1",
|
| 8 |
+
"ScoopWater-v1",
|
| 9 |
+
"StraightenTwoRopesSequential-v1",
|
| 10 |
+
"ClothWipe-v1",
|
| 11 |
+
"RollingPin-v1",
|
| 12 |
+
"RopeBridgeDex-v1",
|
| 13 |
+
"DualArmClothAlign-v1",
|
| 14 |
+
"DualArmPushObject-v1",
|
| 15 |
+
"DualArmStraightenRope-v1",
|
| 16 |
+
"DualArmPlaceRopeOverRod-v1",
|
| 17 |
+
"DualArmStuffCloth-v1",
|
| 18 |
+
"DualArmPouringTwoCups-v1"
|
| 19 |
+
],
|
| 20 |
+
"experiment": "suite transfer: continue the finished level-2 subset policy of another grouping on this suite's tasks",
|
| 21 |
+
"method": "PI0.5 LoRA + trainable weights, multi-task (one policy for all tasks in the suite)",
|
| 22 |
+
"base_checkpoint": "gs://openpi-assets/checkpoints/pi05_base/params",
|
| 23 |
+
"init_from": {
|
| 24 |
+
"suite": "level2_rigid",
|
| 25 |
+
"campaign": "pi05_lv2sub_20261029",
|
| 26 |
+
"commit": "6418366a27087db3f6b1bbabcb3aea6beca649e4",
|
| 27 |
+
"npz": "multi_task/level2_rigid/lora_step_0050000.npz",
|
| 28 |
+
"npz_sha256": "51fd5f209443986f40ff7168b3ebde67465ffc8ce9f4b0b763f48f1be5534ec6",
|
| 29 |
+
"local_params": "/mnt1/Object_World_Dataset/gck_pi05_lv2sub/checkpoints/maniladder_pi05_lora/pi05_lora_l2rigid/50000/params",
|
| 30 |
+
"mean_success_rate_on_own_tasks": 0.17250000000000004,
|
| 31 |
+
"note": "training started from ALL parameters of the final level2_rigid checkpoint (= pi05_base + its lora_step_0050000.npz trainable tensors), i.e. LoRA and the trained vision/action layers continue from that policy; optimizer state and lr schedule restart"
|
| 32 |
+
},
|
| 33 |
+
"target_suite": "level2_deformable",
|
| 34 |
+
"source_suite": "level2_rigid",
|
| 35 |
+
"checkpoints": [
|
| 36 |
+
{
|
| 37 |
+
"file": "lora_step_0010000.npz",
|
| 38 |
+
"step": 10000,
|
| 39 |
+
"sha256": "b59c5e3a39555e0fc9d2edb6e127ea5a763e21c6e5e4dc4183db56289ac0612f",
|
| 40 |
+
"bytes": 1867943218,
|
| 41 |
+
"evaluated": false
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"file": "lora_step_0020000.npz",
|
| 45 |
+
"step": 20000,
|
| 46 |
+
"sha256": "14a26b031de747f89f7298e5b8d5dc5d88127919e6e0d39a39b289f135229f4f",
|
| 47 |
+
"bytes": 1867943218,
|
| 48 |
+
"evaluated": false
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"file": "lora_step_0030000.npz",
|
| 52 |
+
"step": 30000,
|
| 53 |
+
"sha256": "92653f72cbb35bee686f300ca65b39ca4304c698c94a12594828a4bba9466242",
|
| 54 |
+
"bytes": 1867943218,
|
| 55 |
+
"evaluated": false
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"file": "lora_step_0040000.npz",
|
| 59 |
+
"step": 40000,
|
| 60 |
+
"sha256": "b1571b7d1519a79dd9d4185ad2b8ac7f7689a774c9605fba51b4087d203e0524",
|
| 61 |
+
"bytes": 1867943218,
|
| 62 |
+
"evaluated": false
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"file": "lora_step_0050000.npz",
|
| 66 |
+
"step": 50000,
|
| 67 |
+
"sha256": "9665a5e298c5ff6ce7c05b97c45d97f524e32f6b6e76b6bd4d269bd78b0155a5",
|
| 68 |
+
"bytes": 1867943218,
|
| 69 |
+
"evaluated": true
|
| 70 |
+
}
|
| 71 |
+
],
|
| 72 |
+
"evaluated_checkpoint": "lora_step_0050000.npz",
|
| 73 |
+
"tensor_count": 51,
|
| 74 |
+
"action_dim": 44,
|
| 75 |
+
"state_dim": 44,
|
| 76 |
+
"action_dim_note": "44 = union of all level-2 embodiments (dual-arm dexterous); narrower embodiments are zero-padded",
|
| 77 |
+
"action_horizon": 50,
|
| 78 |
+
"max_token_len": 200,
|
| 79 |
+
"image_size": 224,
|
| 80 |
+
"exec_steps": 16,
|
| 81 |
+
"sample_steps": 10,
|
| 82 |
+
"control_mode": "pd_ee_delta_pose",
|
| 83 |
+
"state_input": "zero vector",
|
| 84 |
+
"cameras": [
|
| 85 |
+
"front_camera",
|
| 86 |
+
"robot_camera",
|
| 87 |
+
"robot_camera_0",
|
| 88 |
+
"robot_camera_1"
|
| 89 |
+
],
|
| 90 |
+
"missing_right_wrist_image": "zeros",
|
| 91 |
+
"num_demos_per_task": 20,
|
| 92 |
+
"train_episodes": 240,
|
| 93 |
+
"train_frames": 94166,
|
| 94 |
+
"train_steps": 50000,
|
| 95 |
+
"batch_size": 64,
|
| 96 |
+
"lr": 5e-05,
|
| 97 |
+
"warmup_steps": 1000,
|
| 98 |
+
"lr_schedule": "cosine decay over all 50000 steps to 5e-6 (fresh schedule, not a continuation of the source run)",
|
| 99 |
+
"data_parallel": "pure data parallel (fsdp_devices=1), 4-8 GPUs, global batch 64",
|
| 100 |
+
"norm_stats_file": "norm_stats.json",
|
| 101 |
+
"norm_stats_sha256": "54e87241dfddc4a1ac0b306dbac306ac745ed0e95b6cf0b41d6ce4767f6ace95",
|
| 102 |
+
"norm_stats_note": "the level2_deformable statistics of pi05_lv2sub_20261029 (same frames); padded dims repaired",
|
| 103 |
+
"training_data": "Linslab/ManiLadder_Dataset raw/<task>, 20 demos per task (12 tasks, 240 episodes, 94166 frames)",
|
| 104 |
+
"task_sources": {
|
| 105 |
+
"FoldShirt-v1": {
|
| 106 |
+
"path": "maniladder/envs/deformable/single_arm_gripper/level_2/fold_shirt.py",
|
| 107 |
+
"sha256": "7e6a310b17fbec618f3026aefdd7e0aa2b2ae3fda1202d37fb3ff156ab2ba7fd",
|
| 108 |
+
"level": "level_2",
|
| 109 |
+
"category": "deformable/single_arm_gripper",
|
| 110 |
+
"cameras": [
|
| 111 |
+
"front_camera",
|
| 112 |
+
"robot_camera",
|
| 113 |
+
null
|
| 114 |
+
]
|
| 115 |
+
},
|
| 116 |
+
"ScoopWater-v1": {
|
| 117 |
+
"path": "maniladder/envs/deformable/single_arm_gripper/level_2/scoop_water.py",
|
| 118 |
+
"sha256": "250d33381060b9e4f0f0e2b3f38fd3e365872ee159fbeeee6f66de5a64a3d167",
|
| 119 |
+
"level": "level_2",
|
| 120 |
+
"category": "deformable/single_arm_gripper",
|
| 121 |
+
"cameras": [
|
| 122 |
+
"front_camera",
|
| 123 |
+
"robot_camera",
|
| 124 |
+
null
|
| 125 |
+
]
|
| 126 |
+
},
|
| 127 |
+
"StraightenTwoRopesSequential-v1": {
|
| 128 |
+
"path": "maniladder/envs/deformable/single_arm_gripper/level_2/straighten_two_rope.py",
|
| 129 |
+
"sha256": "7c5a2e562811d68514a730933f5d15c132fb007f0c29ce299e8b111a60abb1ab",
|
| 130 |
+
"level": "level_2",
|
| 131 |
+
"category": "deformable/single_arm_gripper",
|
| 132 |
+
"cameras": [
|
| 133 |
+
"front_camera",
|
| 134 |
+
"robot_camera",
|
| 135 |
+
null
|
| 136 |
+
]
|
| 137 |
+
},
|
| 138 |
+
"ClothWipe-v1": {
|
| 139 |
+
"path": "maniladder/envs/deformable/single_arm_dex/level_2/cloth_wipe.py",
|
| 140 |
+
"sha256": "45ce8bb2815accba3fae96c9411bc24a4c176607691392b121c31c75ebf6d9e4",
|
| 141 |
+
"level": "level_2",
|
| 142 |
+
"category": "deformable/single_arm_dex",
|
| 143 |
+
"cameras": [
|
| 144 |
+
"front_camera",
|
| 145 |
+
"robot_camera",
|
| 146 |
+
null
|
| 147 |
+
]
|
| 148 |
+
},
|
| 149 |
+
"RollingPin-v1": {
|
| 150 |
+
"path": "maniladder/envs/deformable/single_arm_dex/level_2/rooling_pin.py",
|
| 151 |
+
"sha256": "b8d9b39ad2753b9e8f97b8d9117ba1c1c6c16005d90cbab3c8fa30505b4fb62f",
|
| 152 |
+
"level": "level_2",
|
| 153 |
+
"category": "deformable/single_arm_dex",
|
| 154 |
+
"cameras": [
|
| 155 |
+
"front_camera",
|
| 156 |
+
"robot_camera",
|
| 157 |
+
null
|
| 158 |
+
]
|
| 159 |
+
},
|
| 160 |
+
"RopeBridgeDex-v1": {
|
| 161 |
+
"path": "maniladder/envs/deformable/single_arm_dex/level_2/rope_bridge.py",
|
| 162 |
+
"sha256": "bdae492d46519fea218838c421eb3217df1dea4ecd0ec2358df099f4dfc2765f",
|
| 163 |
+
"level": "level_2",
|
| 164 |
+
"category": "deformable/single_arm_dex",
|
| 165 |
+
"cameras": [
|
| 166 |
+
"front_camera",
|
| 167 |
+
"robot_camera",
|
| 168 |
+
null
|
| 169 |
+
]
|
| 170 |
+
},
|
| 171 |
+
"DualArmClothAlign-v1": {
|
| 172 |
+
"path": "maniladder/envs/deformable/dual_arm_gripper/level_2/cloth_align.py",
|
| 173 |
+
"sha256": "9f65e9339bd9b64ab708a1acfbf5780c14c0ab553ef0d83ba4cfe32b5a987748",
|
| 174 |
+
"level": "level_2",
|
| 175 |
+
"category": "deformable/dual_arm_gripper",
|
| 176 |
+
"cameras": [
|
| 177 |
+
"front_camera",
|
| 178 |
+
"robot_camera_0",
|
| 179 |
+
"robot_camera_1"
|
| 180 |
+
]
|
| 181 |
+
},
|
| 182 |
+
"DualArmPushObject-v1": {
|
| 183 |
+
"path": "maniladder/envs/deformable/dual_arm_gripper/level_2/push_object.py",
|
| 184 |
+
"sha256": "3f0cf62ba9ad3f2b6e93d3808fd68b11a810ed6b7eedea063c922059afbc5ab6",
|
| 185 |
+
"level": "level_2",
|
| 186 |
+
"category": "deformable/dual_arm_gripper",
|
| 187 |
+
"cameras": [
|
| 188 |
+
"front_camera",
|
| 189 |
+
"robot_camera_0",
|
| 190 |
+
"robot_camera_1"
|
| 191 |
+
]
|
| 192 |
+
},
|
| 193 |
+
"DualArmStraightenRope-v1": {
|
| 194 |
+
"path": "maniladder/envs/deformable/dual_arm_gripper/level_2/straighten_rope_dual.py",
|
| 195 |
+
"sha256": "fae8f4feb83db36e70574f232d3c6faab0d7fbc43a5dac2cb13fd8bc13207314",
|
| 196 |
+
"level": "level_2",
|
| 197 |
+
"category": "deformable/dual_arm_gripper",
|
| 198 |
+
"cameras": [
|
| 199 |
+
"front_camera",
|
| 200 |
+
"robot_camera_0",
|
| 201 |
+
"robot_camera_1"
|
| 202 |
+
]
|
| 203 |
+
},
|
| 204 |
+
"DualArmPlaceRopeOverRod-v1": {
|
| 205 |
+
"path": "maniladder/envs/deformable/dual_arm_dex/level_2/drape_rope.py",
|
| 206 |
+
"sha256": "670f1e36c3cd79cbce17b8e6a6fd5edd57816b15dcd8aad748be5a669b8fe14c",
|
| 207 |
+
"level": "level_2",
|
| 208 |
+
"category": "deformable/dual_arm_dex",
|
| 209 |
+
"cameras": [
|
| 210 |
+
"front_camera",
|
| 211 |
+
"robot_camera_0",
|
| 212 |
+
"robot_camera_1"
|
| 213 |
+
]
|
| 214 |
+
},
|
| 215 |
+
"DualArmStuffCloth-v1": {
|
| 216 |
+
"path": "maniladder/envs/deformable/dual_arm_dex/level_2/stuff_cloth.py",
|
| 217 |
+
"sha256": "5b93ca100fb7b035fa07f9c334e1dce162baf7915a1bbf56cae0f1d78f5d56f8",
|
| 218 |
+
"level": "level_2",
|
| 219 |
+
"category": "deformable/dual_arm_dex",
|
| 220 |
+
"cameras": [
|
| 221 |
+
"front_camera",
|
| 222 |
+
"robot_camera_0",
|
| 223 |
+
"robot_camera_1"
|
| 224 |
+
]
|
| 225 |
+
},
|
| 226 |
+
"DualArmPouringTwoCups-v1": {
|
| 227 |
+
"path": "maniladder/envs/deformable/dual_arm_dex/level_2/water_cup.py",
|
| 228 |
+
"sha256": "4ac7b0bf11eecec6703389831a8711f66875b4dbfedbe6ab8a5faf04ceb9281d",
|
| 229 |
+
"level": "level_2",
|
| 230 |
+
"category": "deformable/dual_arm_dex",
|
| 231 |
+
"cameras": [
|
| 232 |
+
"front_camera",
|
| 233 |
+
"robot_camera_0",
|
| 234 |
+
"robot_camera_1"
|
| 235 |
+
]
|
| 236 |
+
}
|
| 237 |
+
},
|
| 238 |
+
"eval_episodes": 50,
|
| 239 |
+
"eval_seed_base": 1000,
|
| 240 |
+
"evaluated_steps": [
|
| 241 |
+
50000
|
| 242 |
+
],
|
| 243 |
+
"selection": "final checkpoint only (no checkpoint selection)",
|
| 244 |
+
"eval_status": "pending (eval_result.json and eval_reports/ are added when the 50-episode sweep finishes)"
|
| 245 |
+
}
|
multi_task/level2_deformable_from_rigid/norm_stats.json
ADDED
|
@@ -0,0 +1,376 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"norm_stats": {
|
| 3 |
+
"state": {
|
| 4 |
+
"mean": [
|
| 5 |
+
0.0,
|
| 6 |
+
0.0,
|
| 7 |
+
0.0,
|
| 8 |
+
0.0,
|
| 9 |
+
0.0,
|
| 10 |
+
0.0,
|
| 11 |
+
0.0,
|
| 12 |
+
0.0,
|
| 13 |
+
0.0,
|
| 14 |
+
0.0,
|
| 15 |
+
0.0,
|
| 16 |
+
0.0,
|
| 17 |
+
0.0,
|
| 18 |
+
0.0,
|
| 19 |
+
0.0,
|
| 20 |
+
0.0,
|
| 21 |
+
0.0,
|
| 22 |
+
0.0,
|
| 23 |
+
0.0,
|
| 24 |
+
0.0,
|
| 25 |
+
0.0,
|
| 26 |
+
0.0,
|
| 27 |
+
0.0,
|
| 28 |
+
0.0,
|
| 29 |
+
0.0,
|
| 30 |
+
0.0,
|
| 31 |
+
0.0,
|
| 32 |
+
0.0,
|
| 33 |
+
0.0,
|
| 34 |
+
0.0,
|
| 35 |
+
0.0,
|
| 36 |
+
0.0,
|
| 37 |
+
0.0,
|
| 38 |
+
0.0,
|
| 39 |
+
0.0,
|
| 40 |
+
0.0,
|
| 41 |
+
0.0,
|
| 42 |
+
0.0,
|
| 43 |
+
0.0,
|
| 44 |
+
0.0,
|
| 45 |
+
0.0,
|
| 46 |
+
0.0,
|
| 47 |
+
0.0,
|
| 48 |
+
0.0
|
| 49 |
+
],
|
| 50 |
+
"std": [
|
| 51 |
+
0.0,
|
| 52 |
+
0.0,
|
| 53 |
+
0.0,
|
| 54 |
+
0.0,
|
| 55 |
+
0.0,
|
| 56 |
+
0.0,
|
| 57 |
+
0.0,
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
0.0,
|
| 62 |
+
0.0,
|
| 63 |
+
0.0,
|
| 64 |
+
0.0,
|
| 65 |
+
0.0,
|
| 66 |
+
0.0,
|
| 67 |
+
0.0,
|
| 68 |
+
0.0,
|
| 69 |
+
0.0,
|
| 70 |
+
0.0,
|
| 71 |
+
0.0,
|
| 72 |
+
0.0,
|
| 73 |
+
0.0,
|
| 74 |
+
0.0,
|
| 75 |
+
0.0,
|
| 76 |
+
0.0,
|
| 77 |
+
0.0,
|
| 78 |
+
0.0,
|
| 79 |
+
0.0,
|
| 80 |
+
0.0,
|
| 81 |
+
0.0,
|
| 82 |
+
0.0,
|
| 83 |
+
0.0,
|
| 84 |
+
0.0,
|
| 85 |
+
0.0,
|
| 86 |
+
0.0,
|
| 87 |
+
0.0,
|
| 88 |
+
0.0,
|
| 89 |
+
0.0,
|
| 90 |
+
0.0,
|
| 91 |
+
0.0,
|
| 92 |
+
0.0,
|
| 93 |
+
0.0,
|
| 94 |
+
0.0
|
| 95 |
+
],
|
| 96 |
+
"q01": [
|
| 97 |
+
0.0,
|
| 98 |
+
0.0,
|
| 99 |
+
0.0,
|
| 100 |
+
0.0,
|
| 101 |
+
0.0,
|
| 102 |
+
0.0,
|
| 103 |
+
0.0,
|
| 104 |
+
0.0,
|
| 105 |
+
0.0,
|
| 106 |
+
0.0,
|
| 107 |
+
0.0,
|
| 108 |
+
0.0,
|
| 109 |
+
0.0,
|
| 110 |
+
0.0,
|
| 111 |
+
0.0,
|
| 112 |
+
0.0,
|
| 113 |
+
0.0,
|
| 114 |
+
0.0,
|
| 115 |
+
0.0,
|
| 116 |
+
0.0,
|
| 117 |
+
0.0,
|
| 118 |
+
0.0,
|
| 119 |
+
0.0,
|
| 120 |
+
0.0,
|
| 121 |
+
0.0,
|
| 122 |
+
0.0,
|
| 123 |
+
0.0,
|
| 124 |
+
0.0,
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
0.0,
|
| 129 |
+
0.0,
|
| 130 |
+
0.0,
|
| 131 |
+
0.0,
|
| 132 |
+
0.0,
|
| 133 |
+
0.0,
|
| 134 |
+
0.0,
|
| 135 |
+
0.0,
|
| 136 |
+
0.0,
|
| 137 |
+
0.0,
|
| 138 |
+
0.0,
|
| 139 |
+
0.0,
|
| 140 |
+
0.0
|
| 141 |
+
],
|
| 142 |
+
"q99": [
|
| 143 |
+
0.0,
|
| 144 |
+
0.0,
|
| 145 |
+
0.0,
|
| 146 |
+
0.0,
|
| 147 |
+
0.0,
|
| 148 |
+
0.0,
|
| 149 |
+
0.0,
|
| 150 |
+
0.0,
|
| 151 |
+
0.0,
|
| 152 |
+
0.0,
|
| 153 |
+
0.0,
|
| 154 |
+
0.0,
|
| 155 |
+
0.0,
|
| 156 |
+
0.0,
|
| 157 |
+
0.0,
|
| 158 |
+
0.0,
|
| 159 |
+
0.0,
|
| 160 |
+
0.0,
|
| 161 |
+
0.0,
|
| 162 |
+
0.0,
|
| 163 |
+
0.0,
|
| 164 |
+
0.0,
|
| 165 |
+
0.0,
|
| 166 |
+
0.0,
|
| 167 |
+
0.0,
|
| 168 |
+
0.0,
|
| 169 |
+
0.0,
|
| 170 |
+
0.0,
|
| 171 |
+
0.0,
|
| 172 |
+
0.0,
|
| 173 |
+
0.0,
|
| 174 |
+
0.0,
|
| 175 |
+
0.0,
|
| 176 |
+
0.0,
|
| 177 |
+
0.0,
|
| 178 |
+
0.0,
|
| 179 |
+
0.0,
|
| 180 |
+
0.0,
|
| 181 |
+
0.0,
|
| 182 |
+
0.0,
|
| 183 |
+
0.0,
|
| 184 |
+
0.0,
|
| 185 |
+
0.0,
|
| 186 |
+
0.0
|
| 187 |
+
]
|
| 188 |
+
},
|
| 189 |
+
"actions": {
|
| 190 |
+
"mean": [
|
| 191 |
+
0.0013269251212477684,
|
| 192 |
+
-0.0010167420841753483,
|
| 193 |
+
-0.006871579214930534,
|
| 194 |
+
0.002251440193504095,
|
| 195 |
+
0.0000821183348307386,
|
| 196 |
+
-0.0001825987856136635,
|
| 197 |
+
-0.02152448706328869,
|
| 198 |
+
0.08960748463869095,
|
| 199 |
+
0.08575636148452759,
|
| 200 |
+
0.04358629882335663,
|
| 201 |
+
-0.00004178237577434629,
|
| 202 |
+
0.06242834031581879,
|
| 203 |
+
0.07320564240217209,
|
| 204 |
+
-0.03259982541203499,
|
| 205 |
+
0.002032879739999771,
|
| 206 |
+
0.047316424548625946,
|
| 207 |
+
0.07990769296884537,
|
| 208 |
+
0.05248448625206947,
|
| 209 |
+
0.023005589842796326,
|
| 210 |
+
-0.031872451305389404,
|
| 211 |
+
0.10320694744586945,
|
| 212 |
+
0.050701990723609924,
|
| 213 |
+
-0.0008492753840982914,
|
| 214 |
+
0.0005983017617836595,
|
| 215 |
+
-0.0007291046204045415,
|
| 216 |
+
-0.000936629599891603,
|
| 217 |
+
0.0003520831814967096,
|
| 218 |
+
-0.0011530725751072168,
|
| 219 |
+
0.0011414290638640523,
|
| 220 |
+
0.08363783359527588,
|
| 221 |
+
0.08739026635885239,
|
| 222 |
+
0.04650195688009262,
|
| 223 |
+
0.0027384806890040636,
|
| 224 |
+
0.06453003734350204,
|
| 225 |
+
0.08419813960790634,
|
| 226 |
+
0.057139504700899124,
|
| 227 |
+
0.0025265805888921022,
|
| 228 |
+
0.047478001564741135,
|
| 229 |
+
0.08424048125743866,
|
| 230 |
+
0.05882285162806511,
|
| 231 |
+
-0.03025839850306511,
|
| 232 |
+
0.023318108171224594,
|
| 233 |
+
0.09852747619152069,
|
| 234 |
+
0.0588659830391407
|
| 235 |
+
],
|
| 236 |
+
"std": [
|
| 237 |
+
0.06506874412298203,
|
| 238 |
+
0.07978043705224991,
|
| 239 |
+
0.08339080214500427,
|
| 240 |
+
0.03707493096590042,
|
| 241 |
+
0.02758833020925522,
|
| 242 |
+
0.019669050350785255,
|
| 243 |
+
0.6307249069213867,
|
| 244 |
+
0.25917360186576843,
|
| 245 |
+
0.26798275113105774,
|
| 246 |
+
0.15916167199611664,
|
| 247 |
+
0.007993180304765701,
|
| 248 |
+
0.214180126786232,
|
| 249 |
+
0.25014981627464294,
|
| 250 |
+
0.44462549686431885,
|
| 251 |
+
0.01617257483303547,
|
| 252 |
+
0.17469458281993866,
|
| 253 |
+
0.2674095332622528,
|
| 254 |
+
0.1891099214553833,
|
| 255 |
+
0.12104544788599014,
|
| 256 |
+
0.13247665762901306,
|
| 257 |
+
0.2698949873447418,
|
| 258 |
+
0.16648833453655243,
|
| 259 |
+
0.05136749520897865,
|
| 260 |
+
0.04319773614406586,
|
| 261 |
+
0.054399069398641586,
|
| 262 |
+
0.00800393708050251,
|
| 263 |
+
0.02376396767795086,
|
| 264 |
+
0.012873859144747257,
|
| 265 |
+
0.0239039808511734,
|
| 266 |
+
0.2513743042945862,
|
| 267 |
+
0.28016096353530884,
|
| 268 |
+
0.15870502591133118,
|
| 269 |
+
0.013302752748131752,
|
| 270 |
+
0.2125566601753235,
|
| 271 |
+
0.2812312841415405,
|
| 272 |
+
0.1933852732181549,
|
| 273 |
+
0.011450414545834064,
|
| 274 |
+
0.16105464100837708,
|
| 275 |
+
0.2812013030052185,
|
| 276 |
+
0.19848212599754333,
|
| 277 |
+
0.13542786240577698,
|
| 278 |
+
0.11882820725440979,
|
| 279 |
+
0.2842475473880768,
|
| 280 |
+
0.182008296251297
|
| 281 |
+
],
|
| 282 |
+
"q01": [
|
| 283 |
+
-0.30001999489068987,
|
| 284 |
+
-0.30001999489068987,
|
| 285 |
+
-0.30001999489068987,
|
| 286 |
+
-0.15008000223636628,
|
| 287 |
+
-0.12006000477075576,
|
| 288 |
+
-0.07512000298500061,
|
| 289 |
+
-1.0,
|
| 290 |
+
-0.246,
|
| 291 |
+
-0.22999999999999998,
|
| 292 |
+
-0.27159999999999995,
|
| 293 |
+
-0.024977841436862963,
|
| 294 |
+
-0.30479999999999996,
|
| 295 |
+
-0.24359999999999993,
|
| 296 |
+
-1.0,
|
| 297 |
+
-0.0183622043967247,
|
| 298 |
+
-0.33599999999999997,
|
| 299 |
+
-0.24480000000000002,
|
| 300 |
+
-0.28159999999999996,
|
| 301 |
+
-0.1904,
|
| 302 |
+
-0.5568,
|
| 303 |
+
-0.19119999999999993,
|
| 304 |
+
-0.30279999999999996,
|
| 305 |
+
-0.19333999670743943,
|
| 306 |
+
-0.13005999778509142,
|
| 307 |
+
-0.33963999421596525,
|
| 308 |
+
-0.10995905101299286,
|
| 309 |
+
-0.11999999731779099,
|
| 310 |
+
-0.11999999731779099,
|
| 311 |
+
-0.03954988718032837,
|
| 312 |
+
-0.11280000000000001,
|
| 313 |
+
-0.124,
|
| 314 |
+
-0.13359999999999994,
|
| 315 |
+
-0.004831894874572751,
|
| 316 |
+
-0.13839999999999997,
|
| 317 |
+
-0.1452,
|
| 318 |
+
-0.1452,
|
| 319 |
+
-0.0018044939041138575,
|
| 320 |
+
-0.1452,
|
| 321 |
+
-0.1452,
|
| 322 |
+
-0.1452,
|
| 323 |
+
-1.0,
|
| 324 |
+
-0.12519999999999998,
|
| 325 |
+
-0.15559999999999996,
|
| 326 |
+
-0.18279999999999996
|
| 327 |
+
],
|
| 328 |
+
"q99": [
|
| 329 |
+
0.23995999591350547,
|
| 330 |
+
0.23995999591350547,
|
| 331 |
+
0.29987999489307404,
|
| 332 |
+
0.19992000297904017,
|
| 333 |
+
0.11994000476598743,
|
| 334 |
+
0.07494000297784806,
|
| 335 |
+
0.9996,
|
| 336 |
+
0.9996,
|
| 337 |
+
0.9996,
|
| 338 |
+
0.5564,
|
| 339 |
+
0.03766929175853728,
|
| 340 |
+
0.9996,
|
| 341 |
+
0.9996,
|
| 342 |
+
0.9996,
|
| 343 |
+
0.12938458453416823,
|
| 344 |
+
0.8532000000000002,
|
| 345 |
+
0.9996,
|
| 346 |
+
0.6820000000000002,
|
| 347 |
+
0.5708,
|
| 348 |
+
0.12680000000000002,
|
| 349 |
+
0.9996,
|
| 350 |
+
0.5980000000000001,
|
| 351 |
+
0.19207999672889708,
|
| 352 |
+
0.16967999711036685,
|
| 353 |
+
0.16981999710798257,
|
| 354 |
+
0.11999999731779099,
|
| 355 |
+
0.11995199731886386,
|
| 356 |
+
0.11999999731779099,
|
| 357 |
+
0.06689310073852539,
|
| 358 |
+
0.9996,
|
| 359 |
+
0.9996,
|
| 360 |
+
0.5452000000000001,
|
| 361 |
+
0.057328959941864016,
|
| 362 |
+
0.7876000000000001,
|
| 363 |
+
0.9996,
|
| 364 |
+
0.6876,
|
| 365 |
+
0.04338243770599359,
|
| 366 |
+
0.5568000000000002,
|
| 367 |
+
0.9996,
|
| 368 |
+
0.6892,
|
| 369 |
+
0.550000011920929,
|
| 370 |
+
0.43000000000000016,
|
| 371 |
+
0.9996,
|
| 372 |
+
0.6344000000000001
|
| 373 |
+
]
|
| 374 |
+
}
|
| 375 |
+
}
|
| 376 |
+
}
|