innyun's picture
initial commit
c75de68
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0526472330093384,
"min": 1.0526472330093384,
"max": 2.8658008575439453,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10073.833984375,
"min": 10073.833984375,
"max": 29380.19140625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.997503280639648,
"min": 0.45732635259628296,
"max": 12.997503280639648,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2534.51318359375,
"min": 88.7213134765625,
"max": 2643.939453125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.066309943411376,
"min": 0.0637699279227972,
"max": 0.07436238747027614,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.265239773645504,
"min": 0.2550797116911888,
"max": 0.3510775884597987,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.250709986336091,
"min": 0.19503848392872464,
"max": 0.3714096244643716,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.002839945344364,
"min": 0.7801539357148985,
"max": 1.7918025279746335,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000009e-06,
"min": 8.082097306000009e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.2328389224000035e-05,
"min": 3.2328389224000035e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269399999999998,
"min": 0.10269399999999998,
"max": 0.197294,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4107759999999999,
"min": 0.4107759999999999,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.568181818181817,
"min": 3.9318181818181817,
"max": 25.836363636363636,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1125.0,
"min": 173.0,
"max": 1421.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.568181818181817,
"min": 3.9318181818181817,
"max": 25.836363636363636,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1125.0,
"min": 173.0,
"max": 1421.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1697834025",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1697834551"
},
"total": 526.204636625,
"count": 1,
"self": 0.42567755100003524,
"children": {
"run_training.setup": {
"total": 0.04417260200000328,
"count": 1,
"self": 0.04417260200000328
},
"TrainerController.start_learning": {
"total": 525.734786472,
"count": 1,
"self": 0.6092425909981785,
"children": {
"TrainerController._reset_env": {
"total": 1.2464080089999925,
"count": 1,
"self": 1.2464080089999925
},
"TrainerController.advance": {
"total": 523.802892390002,
"count": 18203,
"self": 0.31294260001834573,
"children": {
"env_step": {
"total": 523.4899497899836,
"count": 18203,
"self": 427.8722656109771,
"children": {
"SubprocessEnvManager._take_step": {
"total": 95.31218001700103,
"count": 18203,
"self": 1.5502432270070017,
"children": {
"TorchPolicy.evaluate": {
"total": 93.76193678999402,
"count": 18203,
"self": 93.76193678999402
}
}
},
"workers": {
"total": 0.3055041620054908,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 524.2953818320037,
"count": 18203,
"is_parallel": true,
"self": 278.53897982600137,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005104507999988073,
"count": 1,
"is_parallel": true,
"self": 0.003785484000047745,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013190239999403275,
"count": 10,
"is_parallel": true,
"self": 0.0013190239999403275
}
}
},
"UnityEnvironment.step": {
"total": 0.03390127099999063,
"count": 1,
"is_parallel": true,
"self": 0.0006386619999148024,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039656600000625986,
"count": 1,
"is_parallel": true,
"self": 0.00039656600000625986
},
"communicator.exchange": {
"total": 0.03100684500003581,
"count": 1,
"is_parallel": true,
"self": 0.03100684500003581
},
"steps_from_proto": {
"total": 0.0018591980000337571,
"count": 1,
"is_parallel": true,
"self": 0.0003507180000497101,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001508479999984047,
"count": 10,
"is_parallel": true,
"self": 0.001508479999984047
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 245.75640200600236,
"count": 18202,
"is_parallel": true,
"self": 10.536543607008355,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.7523682309977175,
"count": 18202,
"is_parallel": true,
"self": 5.7523682309977175
},
"communicator.exchange": {
"total": 194.52030778799684,
"count": 18202,
"is_parallel": true,
"self": 194.52030778799684
},
"steps_from_proto": {
"total": 34.94718237999945,
"count": 18202,
"is_parallel": true,
"self": 6.809007592996011,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.138174787003436,
"count": 182020,
"is_parallel": true,
"self": 28.138174787003436
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012296499994590704,
"count": 1,
"self": 0.00012296499994590704,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 520.5069270230226,
"count": 433228,
"is_parallel": true,
"self": 9.06125605102369,
"children": {
"process_trajectory": {
"total": 244.60253514699838,
"count": 433228,
"is_parallel": true,
"self": 243.8499144579984,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7526206889999685,
"count": 4,
"is_parallel": true,
"self": 0.7526206889999685
}
}
},
"_update_policy": {
"total": 266.84313582500056,
"count": 90,
"is_parallel": true,
"self": 87.04891390100306,
"children": {
"TorchPPOOptimizer.update": {
"total": 179.7942219239975,
"count": 7645,
"is_parallel": true,
"self": 179.7942219239975
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.07612051699993572,
"count": 1,
"self": 0.0008926550000296629,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07522786199990605,
"count": 1,
"self": 0.07522786199990605
}
}
}
}
}
}
}