ppo-Huggy / run_logs /timers.json
joelb's picture
Huggy
72e297e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4098517894744873,
"min": 1.4098517894744873,
"max": 1.4288262128829956,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71496.40625,
"min": 69500.9453125,
"max": 76526.7265625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 90.53061224489795,
"min": 88.58408679927668,
"max": 397.3333333333333,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48796.0,
"min": 48796.0,
"max": 50169.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999911.0,
"min": 49696.0,
"max": 1999911.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999911.0,
"min": 49696.0,
"max": 1999911.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.384735345840454,
"min": 0.210429385304451,
"max": 2.5034377574920654,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1285.372314453125,
"min": 26.303672790527344,
"max": 1341.67919921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.728573681029849,
"min": 1.9085817730426788,
"max": 3.9201837654269154,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2009.7012140750885,
"min": 238.57272163033485,
"max": 2106.144686639309,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.728573681029849,
"min": 1.9085817730426788,
"max": 3.9201837654269154,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2009.7012140750885,
"min": 238.57272163033485,
"max": 2106.144686639309,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01918486165684751,
"min": 0.013704095071686122,
"max": 0.02049401099793613,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.057554584970542534,
"min": 0.027408190143372244,
"max": 0.05814962444516519,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04810428913268778,
"min": 0.020282438832024734,
"max": 0.05760888693233331,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14431286739806334,
"min": 0.04056487766404947,
"max": 0.17282666079699993,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.196248934616653e-06,
"min": 3.196248934616653e-06,
"max": 0.00029529517656827497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.588746803849958e-06,
"min": 9.588746803849958e-06,
"max": 0.0008438832187055999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10106538333333336,
"min": 0.10106538333333336,
"max": 0.19843172499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30319615000000005,
"min": 0.20725495000000005,
"max": 0.5812944,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.316262833333312e-05,
"min": 6.316262833333312e-05,
"max": 0.0049217430775000005,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018948788499999937,
"min": 0.00018948788499999937,
"max": 0.014066590560000002,
"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": "1731096464",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1731098875"
},
"total": 2410.48428124,
"count": 1,
"self": 0.4249819470001057,
"children": {
"run_training.setup": {
"total": 0.09297124900001563,
"count": 1,
"self": 0.09297124900001563
},
"TrainerController.start_learning": {
"total": 2409.966328044,
"count": 1,
"self": 4.463581448058449,
"children": {
"TrainerController._reset_env": {
"total": 5.730452417999999,
"count": 1,
"self": 5.730452417999999
},
"TrainerController.advance": {
"total": 2399.6638219649412,
"count": 231756,
"self": 4.506032032963958,
"children": {
"env_step": {
"total": 1891.9540859899664,
"count": 231756,
"self": 1483.3745876981009,
"children": {
"SubprocessEnvManager._take_step": {
"total": 405.90519448097547,
"count": 231756,
"self": 15.52886461903563,
"children": {
"TorchPolicy.evaluate": {
"total": 390.37632986193984,
"count": 223006,
"self": 390.37632986193984
}
}
},
"workers": {
"total": 2.6743038108901374,
"count": 231756,
"self": 0.0,
"children": {
"worker_root": {
"total": 2402.8890582539657,
"count": 231756,
"is_parallel": true,
"self": 1199.1930121769853,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010494320000020707,
"count": 1,
"is_parallel": true,
"self": 0.0003305360000069868,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007188959999950839,
"count": 2,
"is_parallel": true,
"self": 0.0007188959999950839
}
}
},
"UnityEnvironment.step": {
"total": 0.028995048000012957,
"count": 1,
"is_parallel": true,
"self": 0.00042638100001113344,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021781000000942186,
"count": 1,
"is_parallel": true,
"self": 0.00021781000000942186
},
"communicator.exchange": {
"total": 0.027582838999990145,
"count": 1,
"is_parallel": true,
"self": 0.027582838999990145
},
"steps_from_proto": {
"total": 0.0007680180000022574,
"count": 1,
"is_parallel": true,
"self": 0.00019058199998767122,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005774360000145862,
"count": 2,
"is_parallel": true,
"self": 0.0005774360000145862
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1203.6960460769803,
"count": 231755,
"is_parallel": true,
"self": 37.3832597818639,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.45846030504921,
"count": 231755,
"is_parallel": true,
"self": 79.45846030504921
},
"communicator.exchange": {
"total": 1000.5715154769956,
"count": 231755,
"is_parallel": true,
"self": 1000.5715154769956
},
"steps_from_proto": {
"total": 86.2828105130717,
"count": 231755,
"is_parallel": true,
"self": 30.471592460018286,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.81121805305341,
"count": 463510,
"is_parallel": true,
"self": 55.81121805305341
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 503.2037039420111,
"count": 231756,
"self": 6.407912062023115,
"children": {
"process_trajectory": {
"total": 159.71579755298774,
"count": 231756,
"self": 158.42361828098745,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2921792720002827,
"count": 10,
"self": 1.2921792720002827
}
}
},
"_update_policy": {
"total": 337.07999432700024,
"count": 97,
"self": 270.9225240109946,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.15747031600566,
"count": 2910,
"self": 66.15747031600566
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.630002750782296e-07,
"count": 1,
"self": 9.630002750782296e-07
},
"TrainerController._save_models": {
"total": 0.10847125000009328,
"count": 1,
"self": 0.0020676059998550045,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10640364400023827,
"count": 1,
"self": 0.10640364400023827
}
}
}
}
}
}
}