Unclad3610's picture
First Push
2b7f7ac verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6291239261627197,
"min": 0.5652688145637512,
"max": 2.857793092727661,
"count": 100
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6193.72509765625,
"min": 5583.7255859375,
"max": 29203.787109375,
"count": 100
},
"SnowballTarget.Step.mean": {
"value": 999984.0,
"min": 9984.0,
"max": 999984.0,
"count": 100
},
"SnowballTarget.Step.sum": {
"value": 999984.0,
"min": 9984.0,
"max": 999984.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.195591926574707,
"min": 0.33864104747772217,
"max": 14.304688453674316,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 4911.6748046875,
"min": 116.83116149902344,
"max": 5050.4775390625,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.09598512889554996,
"min": 0.09230906890388724,
"max": 0.10381022107649454,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3839405155821998,
"min": 0.36923627561554895,
"max": 0.5137361207859665,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.10335023499860922,
"min": 0.07714333915385732,
"max": 0.19291071240954538,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.4134009399944369,
"min": 0.3085733566154293,
"max": 0.9645535620477269,
"count": 100
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.3764995412000025e-06,
"min": 1.3764995412000025e-06,
"max": 0.00029837640054119997,
"count": 100
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.50599816480001e-06,
"min": 5.50599816480001e-06,
"max": 0.001477032007656,
"count": 100
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10045880000000001,
"min": 0.10045880000000001,
"max": 0.19945880000000005,
"count": 100
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40183520000000006,
"min": 0.40183520000000006,
"max": 0.992344,
"count": 100
},
"SnowballTarget.Policy.Beta.mean": {
"value": 3.289412000000005e-05,
"min": 3.289412000000005e-05,
"max": 0.00497299412,
"count": 100
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0001315764800000002,
"min": 0.0001315764800000002,
"max": 0.0246179656,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 28.11111111111111,
"min": 3.5454545454545454,
"max": 28.204545454545453,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1265.0,
"min": 156.0,
"max": 1546.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 28.11111111111111,
"min": 3.5454545454545454,
"max": 28.204545454545453,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1265.0,
"min": 156.0,
"max": 1546.0,
"count": 100
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1714984578",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714987257"
},
"total": 2678.6896230800003,
"count": 1,
"self": 0.4325851510002394,
"children": {
"run_training.setup": {
"total": 0.07649822400003359,
"count": 1,
"self": 0.07649822400003359
},
"TrainerController.start_learning": {
"total": 2678.1805397050002,
"count": 1,
"self": 2.5748565109875017,
"children": {
"TrainerController._reset_env": {
"total": 3.2465849210000215,
"count": 1,
"self": 3.2465849210000215
},
"TrainerController.advance": {
"total": 2672.268025141013,
"count": 90934,
"self": 1.2111465260213663,
"children": {
"env_step": {
"total": 2671.0568786149915,
"count": 90934,
"self": 2017.3750400788128,
"children": {
"SubprocessEnvManager._take_step": {
"total": 652.0493884100988,
"count": 90934,
"self": 7.1721169501129225,
"children": {
"TorchPolicy.evaluate": {
"total": 644.8772714599859,
"count": 90934,
"self": 644.8772714599859
}
}
},
"workers": {
"total": 1.6324501260799025,
"count": 90934,
"self": 0.0,
"children": {
"worker_root": {
"total": 2672.710580668131,
"count": 90934,
"is_parallel": true,
"self": 1590.402262709188,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007466050999937579,
"count": 1,
"is_parallel": true,
"self": 0.004561976999411854,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002904074000525725,
"count": 10,
"is_parallel": true,
"self": 0.002904074000525725
}
}
},
"UnityEnvironment.step": {
"total": 0.03939328699993894,
"count": 1,
"is_parallel": true,
"self": 0.0006342949998270342,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004151820000970474,
"count": 1,
"is_parallel": true,
"self": 0.0004151820000970474
},
"communicator.exchange": {
"total": 0.03642623799987632,
"count": 1,
"is_parallel": true,
"self": 0.03642623799987632
},
"steps_from_proto": {
"total": 0.0019175720001385343,
"count": 1,
"is_parallel": true,
"self": 0.00038314999983413145,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001534422000304403,
"count": 10,
"is_parallel": true,
"self": 0.001534422000304403
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1082.308317958943,
"count": 90933,
"is_parallel": true,
"self": 50.62290692498459,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 26.689912548025177,
"count": 90933,
"is_parallel": true,
"self": 26.689912548025177
},
"communicator.exchange": {
"total": 839.4120842619727,
"count": 90933,
"is_parallel": true,
"self": 839.4120842619727
},
"steps_from_proto": {
"total": 165.58341422396052,
"count": 90933,
"is_parallel": true,
"self": 30.47056071130146,
"children": {
"_process_rank_one_or_two_observation": {
"total": 135.11285351265906,
"count": 909330,
"is_parallel": true,
"self": 135.11285351265906
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013590899970949977,
"count": 1,
"self": 0.00013590899970949977,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 2640.366206054362,
"count": 3865502,
"is_parallel": true,
"self": 80.91144026619259,
"children": {
"process_trajectory": {
"total": 1432.5530451601692,
"count": 3865502,
"is_parallel": true,
"self": 1432.3128524901692,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24019266999994215,
"count": 1,
"is_parallel": true,
"self": 0.24019266999994215
}
}
},
"_update_policy": {
"total": 1126.901720628,
"count": 454,
"is_parallel": true,
"self": 313.39138106598125,
"children": {
"TorchPPOOptimizer.update": {
"total": 813.5103395620188,
"count": 61736,
"is_parallel": true,
"self": 813.5103395620188
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0909372229998553,
"count": 1,
"self": 0.0010170370001105766,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08992018599974472,
"count": 1,
"self": 0.08992018599974472
}
}
}
}
}
}
}