Huggy-ppo / run_logs /timers.json
iamandrewliao's picture
Huggy
8611a26
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4014166593551636,
"min": 1.4014166593551636,
"max": 1.4244327545166016,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69649.0078125,
"min": 67077.6171875,
"max": 76633.5703125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 124.07444168734492,
"min": 76.90654205607477,
"max": 390.0232558139535,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50002.0,
"min": 48851.0,
"max": 50313.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999820.0,
"min": 49968.0,
"max": 1999820.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999820.0,
"min": 49968.0,
"max": 1999820.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2609245777130127,
"min": 0.08215838670730591,
"max": 2.4709057807922363,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 908.8916625976562,
"min": 10.516273498535156,
"max": 1558.3447265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.2703879712825983,
"min": 1.9134317175485194,
"max": 3.9809598698651882,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1314.6959644556046,
"min": 244.91925984621048,
"max": 2501.885264992714,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.2703879712825983,
"min": 1.9134317175485194,
"max": 3.9809598698651882,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1314.6959644556046,
"min": 244.91925984621048,
"max": 2501.885264992714,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01648336866233472,
"min": 0.014550702971690851,
"max": 0.02050484879469473,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04945010598700416,
"min": 0.030848831649018395,
"max": 0.06151454638408419,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04313519199689229,
"min": 0.022543855166683592,
"max": 0.05988968047830793,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.12940557599067687,
"min": 0.045087710333367184,
"max": 0.1796690414349238,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5098488300833435e-06,
"min": 3.5098488300833435e-06,
"max": 0.00029536515154494994,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0529546490250031e-05,
"min": 1.0529546490250031e-05,
"max": 0.0008439412686862499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116991666666668,
"min": 0.10116991666666668,
"max": 0.19845504999999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30350975,
"min": 0.20753135,
"max": 0.58131375,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.837884166666686e-05,
"min": 6.837884166666686e-05,
"max": 0.004922906995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002051365250000006,
"min": 0.0002051365250000006,
"max": 0.014067556125000002,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1703376672",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703379156"
},
"total": 2484.555461121,
"count": 1,
"self": 0.502200294999966,
"children": {
"run_training.setup": {
"total": 0.05227669800001422,
"count": 1,
"self": 0.05227669800001422
},
"TrainerController.start_learning": {
"total": 2484.000984128,
"count": 1,
"self": 4.666347592011334,
"children": {
"TrainerController._reset_env": {
"total": 3.7032686900000726,
"count": 1,
"self": 3.7032686900000726
},
"TrainerController.advance": {
"total": 2475.509799892988,
"count": 232371,
"self": 4.89737401682487,
"children": {
"env_step": {
"total": 1958.3524522761006,
"count": 232371,
"self": 1622.3766517760832,
"children": {
"SubprocessEnvManager._take_step": {
"total": 332.86158453508017,
"count": 232371,
"self": 16.793870104172356,
"children": {
"TorchPolicy.evaluate": {
"total": 316.0677144309078,
"count": 223056,
"self": 316.0677144309078
}
}
},
"workers": {
"total": 3.1142159649373298,
"count": 232371,
"self": 0.0,
"children": {
"worker_root": {
"total": 2476.335087618012,
"count": 232371,
"is_parallel": true,
"self": 1164.8376844410159,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007436030000462779,
"count": 1,
"is_parallel": true,
"self": 0.0002237480001667791,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005198549998794988,
"count": 2,
"is_parallel": true,
"self": 0.0005198549998794988
}
}
},
"UnityEnvironment.step": {
"total": 0.032460820000096646,
"count": 1,
"is_parallel": true,
"self": 0.00034550899988516903,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022468400004527211,
"count": 1,
"is_parallel": true,
"self": 0.00022468400004527211
},
"communicator.exchange": {
"total": 0.03115499600005478,
"count": 1,
"is_parallel": true,
"self": 0.03115499600005478
},
"steps_from_proto": {
"total": 0.0007356310001114252,
"count": 1,
"is_parallel": true,
"self": 0.0002053540001725196,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005302769999389056,
"count": 2,
"is_parallel": true,
"self": 0.0005302769999389056
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1311.4974031769962,
"count": 232370,
"is_parallel": true,
"self": 41.21843187908735,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.57361209086957,
"count": 232370,
"is_parallel": true,
"self": 82.57361209086957
},
"communicator.exchange": {
"total": 1096.2898816011138,
"count": 232370,
"is_parallel": true,
"self": 1096.2898816011138
},
"steps_from_proto": {
"total": 91.4154776059255,
"count": 232370,
"is_parallel": true,
"self": 31.34425301501335,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.07122459091215,
"count": 464740,
"is_parallel": true,
"self": 60.07122459091215
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 512.2599736000627,
"count": 232371,
"self": 7.216088777014079,
"children": {
"process_trajectory": {
"total": 157.8989818310488,
"count": 232371,
"self": 156.67699559904838,
"children": {
"RLTrainer._checkpoint": {
"total": 1.221986232000404,
"count": 10,
"self": 1.221986232000404
}
}
},
"_update_policy": {
"total": 347.14490299199986,
"count": 97,
"self": 280.77519479199793,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.36970820000192,
"count": 2910,
"self": 66.36970820000192
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.43000031838892e-07,
"count": 1,
"self": 9.43000031838892e-07
},
"TrainerController._save_models": {
"total": 0.12156701000003522,
"count": 1,
"self": 0.0021609649998026725,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11940604500023255,
"count": 1,
"self": 0.11940604500023255
}
}
}
}
}
}
}