ppo-Huggy / run_logs /timers.json
pdejong's picture
Huggy
a1afc2b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.403619408607483,
"min": 1.403619408607483,
"max": 1.4280219078063965,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69776.7265625,
"min": 68957.6875,
"max": 78359.625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.12635379061372,
"min": 86.30823117338004,
"max": 399.536,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49376.0,
"min": 49282.0,
"max": 50001.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999935.0,
"min": 49535.0,
"max": 1999935.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999935.0,
"min": 49535.0,
"max": 1999935.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.438096284866333,
"min": -0.025964202359318733,
"max": 2.438096284866333,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1350.705322265625,
"min": -3.2195611000061035,
"max": 1363.7305908203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7197742568671917,
"min": 1.8134626034767396,
"max": 3.834102534330808,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2060.7549383044243,
"min": 224.86936283111572,
"max": 2123.5559905171394,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7197742568671917,
"min": 1.8134626034767396,
"max": 3.834102534330808,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2060.7549383044243,
"min": 224.86936283111572,
"max": 2123.5559905171394,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017776515957100652,
"min": 0.013664200413647146,
"max": 0.02096921163223063,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05332954787130196,
"min": 0.02732840082729429,
"max": 0.05935326503871086,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06245312181611856,
"min": 0.02469208845868707,
"max": 0.06648209306101005,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18735936544835569,
"min": 0.04938417691737414,
"max": 0.1986652462432782,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.168098943999994e-06,
"min": 3.168098943999994e-06,
"max": 0.0002952939015687,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.504296831999982e-06,
"min": 9.504296831999982e-06,
"max": 0.0008437288687570501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10105599999999999,
"min": 0.10105599999999999,
"max": 0.19843130000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.303168,
"min": 0.20728155000000004,
"max": 0.58124295,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.269439999999987e-05,
"min": 6.269439999999987e-05,
"max": 0.004921721870000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018808319999999963,
"min": 0.00018808319999999963,
"max": 0.014064023205000001,
"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": "1710366350",
"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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1710368896"
},
"total": 2545.799968653,
"count": 1,
"self": 0.4529435070007821,
"children": {
"run_training.setup": {
"total": 0.052841592000049786,
"count": 1,
"self": 0.052841592000049786
},
"TrainerController.start_learning": {
"total": 2545.2941835539996,
"count": 1,
"self": 4.676579701953415,
"children": {
"TrainerController._reset_env": {
"total": 2.979950530999986,
"count": 1,
"self": 2.979950530999986
},
"TrainerController.advance": {
"total": 2537.519863926046,
"count": 231897,
"self": 4.883386665936996,
"children": {
"env_step": {
"total": 2041.3764718811158,
"count": 231897,
"self": 1698.7835854901086,
"children": {
"SubprocessEnvManager._take_step": {
"total": 339.5155734190173,
"count": 231897,
"self": 17.059549147005782,
"children": {
"TorchPolicy.evaluate": {
"total": 322.4560242720115,
"count": 222940,
"self": 322.4560242720115
}
}
},
"workers": {
"total": 3.0773129719898407,
"count": 231897,
"self": 0.0,
"children": {
"worker_root": {
"total": 2537.9681033159554,
"count": 231897,
"is_parallel": true,
"self": 1165.6340562700234,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000874406999855637,
"count": 1,
"is_parallel": true,
"self": 0.0002381839997269708,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006362230001286662,
"count": 2,
"is_parallel": true,
"self": 0.0006362230001286662
}
}
},
"UnityEnvironment.step": {
"total": 0.0338207219999731,
"count": 1,
"is_parallel": true,
"self": 0.0004227100000662176,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002458569999816973,
"count": 1,
"is_parallel": true,
"self": 0.0002458569999816973
},
"communicator.exchange": {
"total": 0.03226156000005176,
"count": 1,
"is_parallel": true,
"self": 0.03226156000005176
},
"steps_from_proto": {
"total": 0.0008905949998734286,
"count": 1,
"is_parallel": true,
"self": 0.00024033599993344978,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006502589999399788,
"count": 2,
"is_parallel": true,
"self": 0.0006502589999399788
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1372.334047045932,
"count": 231896,
"is_parallel": true,
"self": 40.70633604379873,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.66587562500604,
"count": 231896,
"is_parallel": true,
"self": 88.66587562500604
},
"communicator.exchange": {
"total": 1146.985578170157,
"count": 231896,
"is_parallel": true,
"self": 1146.985578170157
},
"steps_from_proto": {
"total": 95.97625720697033,
"count": 231896,
"is_parallel": true,
"self": 35.98378424578732,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.99247296118301,
"count": 463792,
"is_parallel": true,
"self": 59.99247296118301
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 491.2600053789931,
"count": 231897,
"self": 7.013263276116959,
"children": {
"process_trajectory": {
"total": 161.84782813087463,
"count": 231897,
"self": 160.52503546687421,
"children": {
"RLTrainer._checkpoint": {
"total": 1.322792664000417,
"count": 10,
"self": 1.322792664000417
}
}
},
"_update_policy": {
"total": 322.39891397200154,
"count": 97,
"self": 259.0069591930062,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.39195477899534,
"count": 2910,
"self": 63.39195477899534
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.322999979602173e-06,
"count": 1,
"self": 6.322999979602173e-06
},
"TrainerController._save_models": {
"total": 0.11778307199983828,
"count": 1,
"self": 0.002052220999757992,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11573085100008029,
"count": 1,
"self": 0.11573085100008029
}
}
}
}
}
}
}