pabloramesc's picture
First Push
82e108e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8452246785163879,
"min": 0.8452246785163879,
"max": 2.8355495929718018,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8033.015625,
"min": 8033.015625,
"max": 28945.2890625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.222891807556152,
"min": 0.4163689613342285,
"max": 13.222891807556152,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2578.4638671875,
"min": 80.77558135986328,
"max": 2678.013427734375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07277253804889315,
"min": 0.062198005552750596,
"max": 0.07667710918733564,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2910901521955726,
"min": 0.24879202221100238,
"max": 0.37501034244675846,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20474330186113424,
"min": 0.14236156288169177,
"max": 0.28012797981500626,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8189732074445369,
"min": 0.5694462515267671,
"max": 1.3768050220667147,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.954545454545453,
"min": 4.2272727272727275,
"max": 26.4,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1142.0,
"min": 186.0,
"max": 1452.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.954545454545453,
"min": 4.2272727272727275,
"max": 26.4,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1142.0,
"min": 186.0,
"max": 1452.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1762609556",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/pablo/courses/deep-rl-course/unit5/venv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1762610037"
},
"total": 491.3476601589998,
"count": 1,
"self": 10.666918978999547,
"children": {
"run_training.setup": {
"total": 0.01879091800014976,
"count": 1,
"self": 0.01879091800014976
},
"TrainerController.start_learning": {
"total": 480.6619502620001,
"count": 1,
"self": 0.32391124099967783,
"children": {
"TrainerController._reset_env": {
"total": 1.9133770869998443,
"count": 1,
"self": 1.9133770869998443
},
"TrainerController.advance": {
"total": 478.33209663500065,
"count": 18192,
"self": 0.28339833301652106,
"children": {
"env_step": {
"total": 353.96076565798467,
"count": 18192,
"self": 257.8049502389772,
"children": {
"SubprocessEnvManager._take_step": {
"total": 95.94372490402361,
"count": 18192,
"self": 0.8555927980021352,
"children": {
"TorchPolicy.evaluate": {
"total": 95.08813210602148,
"count": 18192,
"self": 95.08813210602148
}
}
},
"workers": {
"total": 0.21209051498385634,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 479.64633248899395,
"count": 18192,
"is_parallel": true,
"self": 240.93424115199082,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001894257000003563,
"count": 1,
"is_parallel": true,
"self": 0.0006709549995775888,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012233020004259743,
"count": 10,
"is_parallel": true,
"self": 0.0012233020004259743
}
}
},
"UnityEnvironment.step": {
"total": 0.022640368000111266,
"count": 1,
"is_parallel": true,
"self": 0.00023260200032382272,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019810399999187212,
"count": 1,
"is_parallel": true,
"self": 0.00019810399999187212
},
"communicator.exchange": {
"total": 0.02155378599991309,
"count": 1,
"is_parallel": true,
"self": 0.02155378599991309
},
"steps_from_proto": {
"total": 0.0006558759998824826,
"count": 1,
"is_parallel": true,
"self": 0.0001512569999704283,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005046189999120543,
"count": 10,
"is_parallel": true,
"self": 0.0005046189999120543
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 238.71209133700313,
"count": 18191,
"is_parallel": true,
"self": 3.917199090988106,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.4620798480036683,
"count": 18191,
"is_parallel": true,
"self": 2.4620798480036683
},
"communicator.exchange": {
"total": 220.11126568699888,
"count": 18191,
"is_parallel": true,
"self": 220.11126568699888
},
"steps_from_proto": {
"total": 12.22154671101248,
"count": 18191,
"is_parallel": true,
"self": 2.7157417359562714,
"children": {
"_process_rank_one_or_two_observation": {
"total": 9.505804975056208,
"count": 181910,
"is_parallel": true,
"self": 9.505804975056208
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.08793264399947,
"count": 18192,
"self": 0.4302321350050988,
"children": {
"process_trajectory": {
"total": 25.582396705995734,
"count": 18192,
"self": 25.20836221599552,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3740344900002128,
"count": 4,
"self": 0.3740344900002128
}
}
},
"_update_policy": {
"total": 98.07530380299863,
"count": 90,
"self": 21.907443468001702,
"children": {
"TorchPPOOptimizer.update": {
"total": 76.16786033499693,
"count": 4587,
"self": 76.16786033499693
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.039998308755457e-07,
"count": 1,
"self": 7.039998308755457e-07
},
"TrainerController._save_models": {
"total": 0.0925645950001126,
"count": 1,
"self": 0.0014865620000819035,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0910780330000307,
"count": 1,
"self": 0.0910780330000307
}
}
}
}
}
}
}