Adi0010's picture
First Push
124c0ef
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0198522806167603,
"min": 1.015032172203064,
"max": 2.8639638423919678,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9726.3310546875,
"min": 9726.3310546875,
"max": 29329.853515625,
"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": 12.858246803283691,
"min": 0.4678295850753784,
"max": 12.858246803283691,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2507.358154296875,
"min": 90.75894165039062,
"max": 2614.220703125,
"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.Losses.PolicyLoss.mean": {
"value": 0.07520668856587315,
"min": 0.06134264996274164,
"max": 0.07650031089820093,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3008267542634926,
"min": 0.24537059985096657,
"max": 0.38250155449100465,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2030753381550312,
"min": 0.10759409535539283,
"max": 0.30163016138123533,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8123013526201248,
"min": 0.4303763814215713,
"max": 1.5081508069061766,
"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.CumulativeReward.mean": {
"value": 25.204545454545453,
"min": 3.25,
"max": 25.6,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 143.0,
"max": 1408.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 3.25,
"max": 25.6,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 143.0,
"max": 1408.0,
"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": "1683286612",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1683287139"
},
"total": 526.800679211,
"count": 1,
"self": 0.42393782600004215,
"children": {
"run_training.setup": {
"total": 0.040505402999997386,
"count": 1,
"self": 0.040505402999997386
},
"TrainerController.start_learning": {
"total": 526.336235982,
"count": 1,
"self": 0.7046973079867485,
"children": {
"TrainerController._reset_env": {
"total": 4.75113925900007,
"count": 1,
"self": 4.75113925900007
},
"TrainerController.advance": {
"total": 520.7308512020135,
"count": 18200,
"self": 0.3505403430177694,
"children": {
"env_step": {
"total": 520.3803108589957,
"count": 18200,
"self": 380.519391275997,
"children": {
"SubprocessEnvManager._take_step": {
"total": 139.51906334499336,
"count": 18200,
"self": 2.046761483003138,
"children": {
"TorchPolicy.evaluate": {
"total": 137.47230186199022,
"count": 18200,
"self": 137.47230186199022
}
}
},
"workers": {
"total": 0.3418562380053345,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 524.4932171229982,
"count": 18200,
"is_parallel": true,
"self": 240.02026377700804,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002081794999980957,
"count": 1,
"is_parallel": true,
"self": 0.0005656450001652047,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015161499998157524,
"count": 10,
"is_parallel": true,
"self": 0.0015161499998157524
}
}
},
"UnityEnvironment.step": {
"total": 0.06873466499996539,
"count": 1,
"is_parallel": true,
"self": 0.0006579269999065218,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003897850000385006,
"count": 1,
"is_parallel": true,
"self": 0.0003897850000385006
},
"communicator.exchange": {
"total": 0.06544145400005164,
"count": 1,
"is_parallel": true,
"self": 0.06544145400005164
},
"steps_from_proto": {
"total": 0.0022454989999687314,
"count": 1,
"is_parallel": true,
"self": 0.0004231699999763805,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018223289999923509,
"count": 10,
"is_parallel": true,
"self": 0.0018223289999923509
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 284.47295334599016,
"count": 18199,
"is_parallel": true,
"self": 10.695592897996562,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.112209217986674,
"count": 18199,
"is_parallel": true,
"self": 6.112209217986674
},
"communicator.exchange": {
"total": 228.80620344600118,
"count": 18199,
"is_parallel": true,
"self": 228.80620344600118
},
"steps_from_proto": {
"total": 38.85894778400575,
"count": 18199,
"is_parallel": true,
"self": 7.79787727598557,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.06107050802018,
"count": 181990,
"is_parallel": true,
"self": 31.06107050802018
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.3982999841318815e-05,
"count": 1,
"self": 4.3982999841318815e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 516.6056049359075,
"count": 482002,
"is_parallel": true,
"self": 11.36166573591197,
"children": {
"process_trajectory": {
"total": 288.13590263899437,
"count": 482002,
"is_parallel": true,
"self": 286.8275758429945,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3083267959998466,
"count": 4,
"is_parallel": true,
"self": 1.3083267959998466
}
}
},
"_update_policy": {
"total": 217.1080365610012,
"count": 90,
"is_parallel": true,
"self": 79.23715562100631,
"children": {
"TorchPPOOptimizer.update": {
"total": 137.8708809399949,
"count": 4587,
"is_parallel": true,
"self": 137.8708809399949
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14950422999982038,
"count": 1,
"self": 0.001092575000029683,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1484116549997907,
"count": 1,
"self": 0.1484116549997907
}
}
}
}
}
}
}