ppo-Huggy / run_logs /timers.json
maxmax99's picture
Huggy
16587d6 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4046725034713745,
"min": 1.404615044593811,
"max": 1.4289684295654297,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70340.3828125,
"min": 68801.625,
"max": 75401.234375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.22093023255815,
"min": 73.2991202346041,
"max": 380.9618320610687,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49497.0,
"min": 48745.0,
"max": 50026.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999430.0,
"min": 49874.0,
"max": 1999430.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999430.0,
"min": 49874.0,
"max": 1999430.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5016894340515137,
"min": 0.1314326524734497,
"max": 2.5329954624176025,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1506.01708984375,
"min": 17.086244583129883,
"max": 1682.26171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9121708646169138,
"min": 1.7600472494959831,
"max": 4.102167269106834,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2355.126860499382,
"min": 228.8061424344778,
"max": 2658.3352349996567,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9121708646169138,
"min": 1.7600472494959831,
"max": 4.102167269106834,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2355.126860499382,
"min": 228.8061424344778,
"max": 2658.3352349996567,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01677280089999032,
"min": 0.012598021618896383,
"max": 0.021170920088641448,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.050318402699970954,
"min": 0.025196043237792766,
"max": 0.06351276026592434,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05506115621990628,
"min": 0.02218787313128511,
"max": 0.06157281833390395,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16518346865971884,
"min": 0.04437574626257022,
"max": 0.17666347399353982,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.79414873531666e-06,
"min": 3.79414873531666e-06,
"max": 0.00029530942656352495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.138244620594998e-05,
"min": 1.138244620594998e-05,
"max": 0.0008437770187409999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10126468333333334,
"min": 0.10126468333333334,
"max": 0.198436475,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30379405000000004,
"min": 0.20770604999999995,
"max": 0.5812590000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.310769833333322e-05,
"min": 7.310769833333322e-05,
"max": 0.004921980102500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021932309499999968,
"min": 0.00021932309499999968,
"max": 0.014064824100000001,
"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": "1724182437",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1724184874"
},
"total": 2437.550375254,
"count": 1,
"self": 0.8460491929999989,
"children": {
"run_training.setup": {
"total": 0.06154226900002868,
"count": 1,
"self": 0.06154226900002868
},
"TrainerController.start_learning": {
"total": 2436.642783792,
"count": 1,
"self": 4.397972787968229,
"children": {
"TrainerController._reset_env": {
"total": 2.619322728000043,
"count": 1,
"self": 2.619322728000043
},
"TrainerController.advance": {
"total": 2429.4555523910317,
"count": 233371,
"self": 4.671534367963886,
"children": {
"env_step": {
"total": 1919.2890910799813,
"count": 233371,
"self": 1586.4505362298758,
"children": {
"SubprocessEnvManager._take_step": {
"total": 329.8965157300056,
"count": 233371,
"self": 18.11451912611801,
"children": {
"TorchPolicy.evaluate": {
"total": 311.7819966038876,
"count": 222993,
"self": 311.7819966038876
}
}
},
"workers": {
"total": 2.9420391200999347,
"count": 233371,
"self": 0.0,
"children": {
"worker_root": {
"total": 2429.1286041709295,
"count": 233371,
"is_parallel": true,
"self": 1150.2319278539558,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010781129999486438,
"count": 1,
"is_parallel": true,
"self": 0.0002690779999738879,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008090349999747559,
"count": 2,
"is_parallel": true,
"self": 0.0008090349999747559
}
}
},
"UnityEnvironment.step": {
"total": 0.0562090050000279,
"count": 1,
"is_parallel": true,
"self": 0.00042408900003465533,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021152099998289486,
"count": 1,
"is_parallel": true,
"self": 0.00021152099998289486
},
"communicator.exchange": {
"total": 0.05111350699985451,
"count": 1,
"is_parallel": true,
"self": 0.05111350699985451
},
"steps_from_proto": {
"total": 0.004459888000155843,
"count": 1,
"is_parallel": true,
"self": 0.00020329099993432465,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004256597000221518,
"count": 2,
"is_parallel": true,
"self": 0.004256597000221518
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1278.8966763169738,
"count": 233370,
"is_parallel": true,
"self": 39.08650051188624,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.78959572505437,
"count": 233370,
"is_parallel": true,
"self": 81.78959572505437
},
"communicator.exchange": {
"total": 1065.4325177579979,
"count": 233370,
"is_parallel": true,
"self": 1065.4325177579979
},
"steps_from_proto": {
"total": 92.58806232203528,
"count": 233370,
"is_parallel": true,
"self": 34.38718660210748,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.20087571992781,
"count": 466740,
"is_parallel": true,
"self": 58.20087571992781
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 505.4949269430863,
"count": 233371,
"self": 6.893166815269069,
"children": {
"process_trajectory": {
"total": 162.96808075581907,
"count": 233371,
"self": 161.51246706881898,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4556136870000955,
"count": 10,
"self": 1.4556136870000955
}
}
},
"_update_policy": {
"total": 335.63367937199814,
"count": 97,
"self": 271.46012743000324,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.1735519419949,
"count": 2910,
"self": 64.1735519419949
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.347000306850532e-06,
"count": 1,
"self": 1.347000306850532e-06
},
"TrainerController._save_models": {
"total": 0.16993453799977942,
"count": 1,
"self": 0.002887855999688327,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1670466820000911,
"count": 1,
"self": 0.1670466820000911
}
}
}
}
}
}
}