Add level2_dexterous_from_gripper (suite transfer: level2_dexterous tasks from the final level2_gripper policy, 50k further steps; evaluation pending)
Browse files- multi_task/level2_dexterous_from_gripper/lora_step_0010000.npz +3 -0
- multi_task/level2_dexterous_from_gripper/lora_step_0020000.npz +3 -0
- multi_task/level2_dexterous_from_gripper/lora_step_0030000.npz +3 -0
- multi_task/level2_dexterous_from_gripper/lora_step_0040000.npz +3 -0
- multi_task/level2_dexterous_from_gripper/lora_step_0050000.npz +3 -0
- multi_task/level2_dexterous_from_gripper/metadata.json +269 -0
- multi_task/level2_dexterous_from_gripper/norm_stats.json +376 -0
multi_task/level2_dexterous_from_gripper/lora_step_0010000.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:daedd8354841e9961c2eaa7124a9336d099310f4c569e9374cb70116ac81afcf
|
| 3 |
+
size 1867943218
|
multi_task/level2_dexterous_from_gripper/lora_step_0020000.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c77de720d81ca6e8da69c81ebde4602b127b1f359be1065576de9094e927911
|
| 3 |
+
size 1867943218
|
multi_task/level2_dexterous_from_gripper/lora_step_0030000.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23a24a6a6fe5518aa513e526bf46f862d927e3af2c90e703c83f4183ecd498d3
|
| 3 |
+
size 1867943218
|
multi_task/level2_dexterous_from_gripper/lora_step_0040000.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c6b59e6e55cfcd23b401b6c86aaca7b921d5e87bbf6800a1f41853c8a939844
|
| 3 |
+
size 1867943218
|
multi_task/level2_dexterous_from_gripper/lora_step_0050000.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:293ec9da93ca5b8b4d532dd35c55cff4b77f39f88ee3c103b2b2533fdfd9e6d9
|
| 3 |
+
size 1867943218
|
multi_task/level2_dexterous_from_gripper/metadata.json
ADDED
|
@@ -0,0 +1,269 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"suite": "level2_dexterous_from_gripper",
|
| 3 |
+
"suite_id": "x_gripper2dex",
|
| 4 |
+
"description": "level2_dexterous tasks, initialised from the final level2_gripper policy (suite transfer), 50k further steps",
|
| 5 |
+
"campaign": "pi05_lv2xfer_20261101",
|
| 6 |
+
"tasks": [
|
| 7 |
+
"GraspTwoBlocks-v1",
|
| 8 |
+
"ReorientPen-v1",
|
| 9 |
+
"DexOpenDoor-v1",
|
| 10 |
+
"HammerNailOut-v1",
|
| 11 |
+
"ClothWipe-v1",
|
| 12 |
+
"RollingPin-v1",
|
| 13 |
+
"RopeBridgeDex-v1",
|
| 14 |
+
"DualArmOpenLaptop-v1",
|
| 15 |
+
"DualArmThrowBlock-v1",
|
| 16 |
+
"DualArmJugglingBall-v1",
|
| 17 |
+
"DualArmOpenBottle-v1",
|
| 18 |
+
"DualArmPlaceRopeOverRod-v1",
|
| 19 |
+
"DualArmStuffCloth-v1",
|
| 20 |
+
"DualArmPouringTwoCups-v1"
|
| 21 |
+
],
|
| 22 |
+
"experiment": "suite transfer: continue the finished level-2 subset policy of another grouping on this suite's tasks",
|
| 23 |
+
"method": "PI0.5 LoRA + trainable weights, multi-task (one policy for all tasks in the suite)",
|
| 24 |
+
"base_checkpoint": "gs://openpi-assets/checkpoints/pi05_base/params",
|
| 25 |
+
"init_from": {
|
| 26 |
+
"suite": "level2_gripper",
|
| 27 |
+
"campaign": "pi05_lv2sub_20261029",
|
| 28 |
+
"commit": "ec4b6e083f09412a55703bdf8acb2720494d19c3",
|
| 29 |
+
"npz": "multi_task/level2_gripper/lora_step_0050000.npz",
|
| 30 |
+
"npz_sha256": "33de9edb557df8fd9dbb569f7f4a97fb0e6b622ba55340543bd79a4cbe6ec62a",
|
| 31 |
+
"local_params": "/mnt1/Object_World_Dataset/gck_pi05_lv2sub/checkpoints/maniladder_pi05_lora/pi05_lora_l2gripper/50000/params",
|
| 32 |
+
"mean_success_rate_on_own_tasks": 0.1657142857142857,
|
| 33 |
+
"note": "training started from ALL parameters of the final level2_gripper 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"
|
| 34 |
+
},
|
| 35 |
+
"target_suite": "level2_dexterous",
|
| 36 |
+
"source_suite": "level2_gripper",
|
| 37 |
+
"checkpoints": [
|
| 38 |
+
{
|
| 39 |
+
"file": "lora_step_0010000.npz",
|
| 40 |
+
"step": 10000,
|
| 41 |
+
"sha256": "daedd8354841e9961c2eaa7124a9336d099310f4c569e9374cb70116ac81afcf",
|
| 42 |
+
"bytes": 1867943218,
|
| 43 |
+
"evaluated": false
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"file": "lora_step_0020000.npz",
|
| 47 |
+
"step": 20000,
|
| 48 |
+
"sha256": "4c77de720d81ca6e8da69c81ebde4602b127b1f359be1065576de9094e927911",
|
| 49 |
+
"bytes": 1867943218,
|
| 50 |
+
"evaluated": false
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"file": "lora_step_0030000.npz",
|
| 54 |
+
"step": 30000,
|
| 55 |
+
"sha256": "23a24a6a6fe5518aa513e526bf46f862d927e3af2c90e703c83f4183ecd498d3",
|
| 56 |
+
"bytes": 1867943218,
|
| 57 |
+
"evaluated": false
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"file": "lora_step_0040000.npz",
|
| 61 |
+
"step": 40000,
|
| 62 |
+
"sha256": "2c6b59e6e55cfcd23b401b6c86aaca7b921d5e87bbf6800a1f41853c8a939844",
|
| 63 |
+
"bytes": 1867943218,
|
| 64 |
+
"evaluated": false
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"file": "lora_step_0050000.npz",
|
| 68 |
+
"step": 50000,
|
| 69 |
+
"sha256": "293ec9da93ca5b8b4d532dd35c55cff4b77f39f88ee3c103b2b2533fdfd9e6d9",
|
| 70 |
+
"bytes": 1867943218,
|
| 71 |
+
"evaluated": true
|
| 72 |
+
}
|
| 73 |
+
],
|
| 74 |
+
"evaluated_checkpoint": "lora_step_0050000.npz",
|
| 75 |
+
"tensor_count": 51,
|
| 76 |
+
"action_dim": 44,
|
| 77 |
+
"state_dim": 44,
|
| 78 |
+
"action_dim_note": "44 = union of all level-2 embodiments (dual-arm dexterous); narrower embodiments are zero-padded",
|
| 79 |
+
"action_horizon": 50,
|
| 80 |
+
"max_token_len": 200,
|
| 81 |
+
"image_size": 224,
|
| 82 |
+
"exec_steps": 16,
|
| 83 |
+
"sample_steps": 10,
|
| 84 |
+
"control_mode": "pd_ee_delta_pose",
|
| 85 |
+
"state_input": "zero vector",
|
| 86 |
+
"cameras": [
|
| 87 |
+
"front_camera",
|
| 88 |
+
"robot_camera",
|
| 89 |
+
"robot_camera_0",
|
| 90 |
+
"robot_camera_1"
|
| 91 |
+
],
|
| 92 |
+
"missing_right_wrist_image": "zeros",
|
| 93 |
+
"num_demos_per_task": 20,
|
| 94 |
+
"train_episodes": 280,
|
| 95 |
+
"train_frames": 122192,
|
| 96 |
+
"train_steps": 50000,
|
| 97 |
+
"batch_size": 64,
|
| 98 |
+
"lr": 5e-05,
|
| 99 |
+
"warmup_steps": 1000,
|
| 100 |
+
"lr_schedule": "cosine decay over all 50000 steps to 5e-6 (fresh schedule, not a continuation of the source run)",
|
| 101 |
+
"data_parallel": "pure data parallel (fsdp_devices=1), 4-8 GPUs, global batch 64",
|
| 102 |
+
"norm_stats_file": "norm_stats.json",
|
| 103 |
+
"norm_stats_sha256": "9397d7156f3f5609f19545d375553f34f430b3fa44336d3e63d32035ff422ba7",
|
| 104 |
+
"norm_stats_note": "the level2_dexterous statistics of pi05_lv2sub_20261029 (same frames); padded dims repaired",
|
| 105 |
+
"training_data": "Linslab/ManiLadder_Dataset raw/<task>, 20 demos per task (14 tasks, 280 episodes, 122192 frames)",
|
| 106 |
+
"task_sources": {
|
| 107 |
+
"GraspTwoBlocks-v1": {
|
| 108 |
+
"path": "maniladder/envs/rigid_body/single_arm_dex/level_2/grasp_blocks.py",
|
| 109 |
+
"sha256": "5ca6052059d89129ea2053033b959eafe590e119664bbcf431143d371650d66e",
|
| 110 |
+
"level": "level_2",
|
| 111 |
+
"category": "rigid_body/single_arm_dex",
|
| 112 |
+
"cameras": [
|
| 113 |
+
"front_camera",
|
| 114 |
+
"robot_camera",
|
| 115 |
+
null
|
| 116 |
+
]
|
| 117 |
+
},
|
| 118 |
+
"ReorientPen-v1": {
|
| 119 |
+
"path": "maniladder/envs/rigid_body/single_arm_dex/level_2/reorient_pen.py",
|
| 120 |
+
"sha256": "cb46bbdf5dc53cc310e613a1556720d34b444b1333421682cd9b5133972aa386",
|
| 121 |
+
"level": "level_2",
|
| 122 |
+
"category": "rigid_body/single_arm_dex",
|
| 123 |
+
"cameras": [
|
| 124 |
+
"front_camera",
|
| 125 |
+
"robot_camera",
|
| 126 |
+
null
|
| 127 |
+
]
|
| 128 |
+
},
|
| 129 |
+
"DexOpenDoor-v1": {
|
| 130 |
+
"path": "maniladder/envs/rigid_body/single_arm_dex/level_2/open_door.py",
|
| 131 |
+
"sha256": "6c21f64c2a98c359f1d01c67743cd590799b763ba3e1b933b7204d798312d062",
|
| 132 |
+
"level": "level_2",
|
| 133 |
+
"category": "rigid_body/single_arm_dex",
|
| 134 |
+
"cameras": [
|
| 135 |
+
"front_camera",
|
| 136 |
+
"robot_camera",
|
| 137 |
+
null
|
| 138 |
+
]
|
| 139 |
+
},
|
| 140 |
+
"HammerNailOut-v1": {
|
| 141 |
+
"path": "maniladder/envs/rigid_body/single_arm_dex/level_2/hammer_nail_out.py",
|
| 142 |
+
"sha256": "f524116a35ee681f0573ed934a47914d71d1ab9ca9cfd610f7d43a574cb8bac4",
|
| 143 |
+
"level": "level_2",
|
| 144 |
+
"category": "rigid_body/single_arm_dex",
|
| 145 |
+
"cameras": [
|
| 146 |
+
"front_camera",
|
| 147 |
+
"robot_camera",
|
| 148 |
+
null
|
| 149 |
+
]
|
| 150 |
+
},
|
| 151 |
+
"ClothWipe-v1": {
|
| 152 |
+
"path": "maniladder/envs/deformable/single_arm_dex/level_2/cloth_wipe.py",
|
| 153 |
+
"sha256": "45ce8bb2815accba3fae96c9411bc24a4c176607691392b121c31c75ebf6d9e4",
|
| 154 |
+
"level": "level_2",
|
| 155 |
+
"category": "deformable/single_arm_dex",
|
| 156 |
+
"cameras": [
|
| 157 |
+
"front_camera",
|
| 158 |
+
"robot_camera",
|
| 159 |
+
null
|
| 160 |
+
]
|
| 161 |
+
},
|
| 162 |
+
"RollingPin-v1": {
|
| 163 |
+
"path": "maniladder/envs/deformable/single_arm_dex/level_2/rooling_pin.py",
|
| 164 |
+
"sha256": "b8d9b39ad2753b9e8f97b8d9117ba1c1c6c16005d90cbab3c8fa30505b4fb62f",
|
| 165 |
+
"level": "level_2",
|
| 166 |
+
"category": "deformable/single_arm_dex",
|
| 167 |
+
"cameras": [
|
| 168 |
+
"front_camera",
|
| 169 |
+
"robot_camera",
|
| 170 |
+
null
|
| 171 |
+
]
|
| 172 |
+
},
|
| 173 |
+
"RopeBridgeDex-v1": {
|
| 174 |
+
"path": "maniladder/envs/deformable/single_arm_dex/level_2/rope_bridge.py",
|
| 175 |
+
"sha256": "bdae492d46519fea218838c421eb3217df1dea4ecd0ec2358df099f4dfc2765f",
|
| 176 |
+
"level": "level_2",
|
| 177 |
+
"category": "deformable/single_arm_dex",
|
| 178 |
+
"cameras": [
|
| 179 |
+
"front_camera",
|
| 180 |
+
"robot_camera",
|
| 181 |
+
null
|
| 182 |
+
]
|
| 183 |
+
},
|
| 184 |
+
"DualArmOpenLaptop-v1": {
|
| 185 |
+
"path": "maniladder/envs/rigid_body/dual_arm_dex/level_2/open_laptop.py",
|
| 186 |
+
"sha256": "e2c3c0714da9a484ed7a7ac3dc6374f61c7e1867167f50b37dca9845534faf93",
|
| 187 |
+
"level": "level_2",
|
| 188 |
+
"category": "rigid_body/dual_arm_dex",
|
| 189 |
+
"cameras": [
|
| 190 |
+
"front_camera",
|
| 191 |
+
"robot_camera_0",
|
| 192 |
+
"robot_camera_1"
|
| 193 |
+
]
|
| 194 |
+
},
|
| 195 |
+
"DualArmThrowBlock-v1": {
|
| 196 |
+
"path": "maniladder/envs/rigid_body/dual_arm_dex/level_2/throw_ball.py",
|
| 197 |
+
"sha256": "0a00a7e724272b98eb42cd58fb57f6e15756a6e115f19f320febda6dda6d7680",
|
| 198 |
+
"level": "level_2",
|
| 199 |
+
"category": "rigid_body/dual_arm_dex",
|
| 200 |
+
"cameras": [
|
| 201 |
+
"front_camera",
|
| 202 |
+
"robot_camera_0",
|
| 203 |
+
"robot_camera_1"
|
| 204 |
+
]
|
| 205 |
+
},
|
| 206 |
+
"DualArmJugglingBall-v1": {
|
| 207 |
+
"path": "maniladder/envs/rigid_body/dual_arm_dex/level_2/juggle_ball.py",
|
| 208 |
+
"sha256": "f5a65ccfa2d7aa379f131628849315ce1840b5e11620e5f6a86c6a3451706ed1",
|
| 209 |
+
"level": "level_2",
|
| 210 |
+
"category": "rigid_body/dual_arm_dex",
|
| 211 |
+
"cameras": [
|
| 212 |
+
"front_camera",
|
| 213 |
+
"robot_camera_0",
|
| 214 |
+
"robot_camera_1"
|
| 215 |
+
]
|
| 216 |
+
},
|
| 217 |
+
"DualArmOpenBottle-v1": {
|
| 218 |
+
"path": "maniladder/envs/rigid_body/dual_arm_dex/level_2/open_bottle.py",
|
| 219 |
+
"sha256": "6c492aff17adfba725a0f605df5394f4fe93e04ef122cf473a210e4a2cf84e2f",
|
| 220 |
+
"level": "level_2",
|
| 221 |
+
"category": "rigid_body/dual_arm_dex",
|
| 222 |
+
"cameras": [
|
| 223 |
+
"front_camera",
|
| 224 |
+
"robot_camera_0",
|
| 225 |
+
"robot_camera_1"
|
| 226 |
+
]
|
| 227 |
+
},
|
| 228 |
+
"DualArmPlaceRopeOverRod-v1": {
|
| 229 |
+
"path": "maniladder/envs/deformable/dual_arm_dex/level_2/drape_rope.py",
|
| 230 |
+
"sha256": "670f1e36c3cd79cbce17b8e6a6fd5edd57816b15dcd8aad748be5a669b8fe14c",
|
| 231 |
+
"level": "level_2",
|
| 232 |
+
"category": "deformable/dual_arm_dex",
|
| 233 |
+
"cameras": [
|
| 234 |
+
"front_camera",
|
| 235 |
+
"robot_camera_0",
|
| 236 |
+
"robot_camera_1"
|
| 237 |
+
]
|
| 238 |
+
},
|
| 239 |
+
"DualArmStuffCloth-v1": {
|
| 240 |
+
"path": "maniladder/envs/deformable/dual_arm_dex/level_2/stuff_cloth.py",
|
| 241 |
+
"sha256": "5b93ca100fb7b035fa07f9c334e1dce162baf7915a1bbf56cae0f1d78f5d56f8",
|
| 242 |
+
"level": "level_2",
|
| 243 |
+
"category": "deformable/dual_arm_dex",
|
| 244 |
+
"cameras": [
|
| 245 |
+
"front_camera",
|
| 246 |
+
"robot_camera_0",
|
| 247 |
+
"robot_camera_1"
|
| 248 |
+
]
|
| 249 |
+
},
|
| 250 |
+
"DualArmPouringTwoCups-v1": {
|
| 251 |
+
"path": "maniladder/envs/deformable/dual_arm_dex/level_2/water_cup.py",
|
| 252 |
+
"sha256": "4ac7b0bf11eecec6703389831a8711f66875b4dbfedbe6ab8a5faf04ceb9281d",
|
| 253 |
+
"level": "level_2",
|
| 254 |
+
"category": "deformable/dual_arm_dex",
|
| 255 |
+
"cameras": [
|
| 256 |
+
"front_camera",
|
| 257 |
+
"robot_camera_0",
|
| 258 |
+
"robot_camera_1"
|
| 259 |
+
]
|
| 260 |
+
}
|
| 261 |
+
},
|
| 262 |
+
"eval_episodes": 50,
|
| 263 |
+
"eval_seed_base": 1000,
|
| 264 |
+
"evaluated_steps": [
|
| 265 |
+
50000
|
| 266 |
+
],
|
| 267 |
+
"selection": "final checkpoint only (no checkpoint selection)",
|
| 268 |
+
"eval_status": "pending (eval_result.json and eval_reports/ are added when the 50-episode sweep finishes)"
|
| 269 |
+
}
|
multi_task/level2_dexterous_from_gripper/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 |
+
-0.0018801151309162378,
|
| 192 |
+
0.0004076742916367948,
|
| 193 |
+
-0.008071891963481903,
|
| 194 |
+
0.0016526260878890753,
|
| 195 |
+
-0.0012841052375733852,
|
| 196 |
+
-0.0013454005820676684,
|
| 197 |
+
-0.0051899803802371025,
|
| 198 |
+
0.08952736109495163,
|
| 199 |
+
0.08520976454019547,
|
| 200 |
+
0.04554983600974083,
|
| 201 |
+
0.00046363193541765213,
|
| 202 |
+
0.06548918038606644,
|
| 203 |
+
0.07380624860525131,
|
| 204 |
+
0.04538995027542114,
|
| 205 |
+
-0.0012439872371032834,
|
| 206 |
+
0.04977956414222717,
|
| 207 |
+
0.07974823564291,
|
| 208 |
+
0.05056856945157051,
|
| 209 |
+
0.03460157290101051,
|
| 210 |
+
-0.02013767696917057,
|
| 211 |
+
0.09719547629356384,
|
| 212 |
+
0.05383921414613724,
|
| 213 |
+
0.0009905502665787935,
|
| 214 |
+
-0.000056831613619579,
|
| 215 |
+
-0.0014422103995457292,
|
| 216 |
+
-0.0009234994067810476,
|
| 217 |
+
0.0002483706921339035,
|
| 218 |
+
-0.0006815713131800294,
|
| 219 |
+
0.0005271200207062066,
|
| 220 |
+
0.06756165623664856,
|
| 221 |
+
0.06867154687643051,
|
| 222 |
+
0.03823808208107948,
|
| 223 |
+
0.0022699348628520966,
|
| 224 |
+
0.052949145436286926,
|
| 225 |
+
0.06701942533254623,
|
| 226 |
+
0.04715820774435997,
|
| 227 |
+
0.002530860947445035,
|
| 228 |
+
0.039265118539333344,
|
| 229 |
+
0.06741517782211304,
|
| 230 |
+
0.04789399728178978,
|
| 231 |
+
0.005173014476895332,
|
| 232 |
+
0.017688943073153496,
|
| 233 |
+
0.09007509052753448,
|
| 234 |
+
0.05633959919214249
|
| 235 |
+
],
|
| 236 |
+
"std": [
|
| 237 |
+
0.05287669599056244,
|
| 238 |
+
0.0621374137699604,
|
| 239 |
+
0.06838520616292953,
|
| 240 |
+
0.04500511288642883,
|
| 241 |
+
0.029881779104471207,
|
| 242 |
+
0.024667387828230858,
|
| 243 |
+
0.06379225105047226,
|
| 244 |
+
0.24780721962451935,
|
| 245 |
+
0.26862019300460815,
|
| 246 |
+
0.1467714160680771,
|
| 247 |
+
0.11527683585882187,
|
| 248 |
+
0.2105255126953125,
|
| 249 |
+
0.2651834189891815,
|
| 250 |
+
0.16967150568962097,
|
| 251 |
+
0.06491546332836151,
|
| 252 |
+
0.17200720310211182,
|
| 253 |
+
0.2796756625175476,
|
| 254 |
+
0.17601749300956726,
|
| 255 |
+
0.1340227872133255,
|
| 256 |
+
0.11974746733903885,
|
| 257 |
+
0.24241045117378235,
|
| 258 |
+
0.15469777584075928,
|
| 259 |
+
0.04996626451611519,
|
| 260 |
+
0.051591429859399796,
|
| 261 |
+
0.06344982236623764,
|
| 262 |
+
0.05542565509676933,
|
| 263 |
+
0.02086525782942772,
|
| 264 |
+
0.011607012711465359,
|
| 265 |
+
0.02139204367995262,
|
| 266 |
+
0.2311318814754486,
|
| 267 |
+
0.24987448751926422,
|
| 268 |
+
0.14720429480075836,
|
| 269 |
+
0.01184222474694252,
|
| 270 |
+
0.19588984549045563,
|
| 271 |
+
0.25177305936813354,
|
| 272 |
+
0.1791539490222931,
|
| 273 |
+
0.02480856515467167,
|
| 274 |
+
0.15260055661201477,
|
| 275 |
+
0.2532307207584381,
|
| 276 |
+
0.18166308104991913,
|
| 277 |
+
0.15717960894107819,
|
| 278 |
+
0.10490428656339645,
|
| 279 |
+
0.25340670347213745,
|
| 280 |
+
0.1652681678533554
|
| 281 |
+
],
|
| 282 |
+
"q01": [
|
| 283 |
+
-0.1502209022164345,
|
| 284 |
+
-0.22788422328233726,
|
| 285 |
+
-0.15022233924865724,
|
| 286 |
+
-0.160172700881958,
|
| 287 |
+
-0.12005710623860355,
|
| 288 |
+
-0.15459299087524414,
|
| 289 |
+
-0.4525478521585464,
|
| 290 |
+
-0.26158188581466657,
|
| 291 |
+
-0.21703091144561792,
|
| 292 |
+
-0.26039999999999996,
|
| 293 |
+
-0.0345206324577334,
|
| 294 |
+
-0.30574123740196235,
|
| 295 |
+
-0.24535083484649656,
|
| 296 |
+
-0.2724,
|
| 297 |
+
-0.0387351155281066,
|
| 298 |
+
-0.3636605062484741,
|
| 299 |
+
-0.2468891072273256,
|
| 300 |
+
-0.2744,
|
| 301 |
+
-0.19615040636062608,
|
| 302 |
+
-0.53,
|
| 303 |
+
-0.19151260108947754,
|
| 304 |
+
-0.27879999999999994,
|
| 305 |
+
-0.17003424899578096,
|
| 306 |
+
-0.13021999500989917,
|
| 307 |
+
-0.3499999940395355,
|
| 308 |
+
-0.3490656912326813,
|
| 309 |
+
-0.11999999731779099,
|
| 310 |
+
-0.11999999731779099,
|
| 311 |
+
-0.036305305600166315,
|
| 312 |
+
-0.1512,
|
| 313 |
+
-0.12359999999999993,
|
| 314 |
+
-0.13879999999999992,
|
| 315 |
+
-0.002481534194946289,
|
| 316 |
+
-0.15599999999999992,
|
| 317 |
+
-0.1452,
|
| 318 |
+
-0.1452,
|
| 319 |
+
-0.0040000000000000036,
|
| 320 |
+
-0.15839999999999999,
|
| 321 |
+
-0.1452,
|
| 322 |
+
-0.1452,
|
| 323 |
+
-0.3932,
|
| 324 |
+
-0.12519999999999998,
|
| 325 |
+
-0.15239999999999998,
|
| 326 |
+
-0.18279999999999996
|
| 327 |
+
],
|
| 328 |
+
"q99": [
|
| 329 |
+
0.12986853015422817,
|
| 330 |
+
0.1491918253719806,
|
| 331 |
+
0.17469095382690425,
|
| 332 |
+
0.41886478662490845,
|
| 333 |
+
0.11220918652713296,
|
| 334 |
+
0.12543106079101562,
|
| 335 |
+
0.04512180948257449,
|
| 336 |
+
0.9997899913787842,
|
| 337 |
+
0.9995641136169429,
|
| 338 |
+
0.5556000000000001,
|
| 339 |
+
0.037827082729339434,
|
| 340 |
+
0.9994303004741667,
|
| 341 |
+
0.9995880451202392,
|
| 342 |
+
0.6796,
|
| 343 |
+
0.11029120922088653,
|
| 344 |
+
0.8486465020179748,
|
| 345 |
+
0.9990528130531313,
|
| 346 |
+
0.6796,
|
| 347 |
+
0.6268903727531434,
|
| 348 |
+
0.11680000000000001,
|
| 349 |
+
0.9994410589218141,
|
| 350 |
+
0.5972000000000002,
|
| 351 |
+
0.1812419012665749,
|
| 352 |
+
0.1697500036656856,
|
| 353 |
+
0.3499999940395355,
|
| 354 |
+
0.11999999731779099,
|
| 355 |
+
0.11995199731886386,
|
| 356 |
+
0.04151220992207527,
|
| 357 |
+
0.016626124072074894,
|
| 358 |
+
0.9628000000000001,
|
| 359 |
+
0.9996,
|
| 360 |
+
0.5432000000000001,
|
| 361 |
+
0.04972121353149414,
|
| 362 |
+
0.7852000000000001,
|
| 363 |
+
0.9996,
|
| 364 |
+
0.6736,
|
| 365 |
+
0.04479999999999995,
|
| 366 |
+
0.5548000000000002,
|
| 367 |
+
0.9996,
|
| 368 |
+
0.6876,
|
| 369 |
+
0.6080000000000001,
|
| 370 |
+
0.42880000000000007,
|
| 371 |
+
0.9996,
|
| 372 |
+
0.6328
|
| 373 |
+
]
|
| 374 |
+
}
|
| 375 |
+
}
|
| 376 |
+
}
|