markeidsaune's picture
First training of SnowballTarget
b48b679
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8673198819160461,
"min": 0.8673198819160461,
"max": 2.8737478256225586,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8319.33203125,
"min": 8319.33203125,
"max": 29524.884765625,
"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": 12.883188247680664,
"min": 0.40927737951278687,
"max": 12.907264709472656,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2512.2216796875,
"min": 79.39981079101562,
"max": 2633.08203125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06813897062880535,
"min": 0.06194995353740239,
"max": 0.07234313666281819,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2725558825152214,
"min": 0.25444169355471913,
"max": 0.361715683314091,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20666183173364283,
"min": 0.10520859837518348,
"max": 0.2994644853998633,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8266473269345713,
"min": 0.4208343935007339,
"max": 1.4973224269993166,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.204545454545453,
"min": 3.0,
"max": 25.431818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 132.0,
"max": 1391.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 3.0,
"max": 25.431818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 132.0,
"max": 1391.0,
"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": "1683662061",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"command_line_arguments": "/home/mark/rl_course/.unit5_venv/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --force --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1683662640"
},
"total": 579.0061066681519,
"count": 1,
"self": 0.3232046333141625,
"children": {
"run_training.setup": {
"total": 0.013338217977434397,
"count": 1,
"self": 0.013338217977434397
},
"TrainerController.start_learning": {
"total": 578.6695638168603,
"count": 1,
"self": 0.48517978843301535,
"children": {
"TrainerController._reset_env": {
"total": 4.797314067836851,
"count": 1,
"self": 4.797314067836851
},
"TrainerController.advance": {
"total": 573.2011918919161,
"count": 18209,
"self": 0.2236510505899787,
"children": {
"env_step": {
"total": 572.9775408413261,
"count": 18209,
"self": 461.97470436245203,
"children": {
"SubprocessEnvManager._take_step": {
"total": 110.74401417281479,
"count": 18209,
"self": 1.4772953810170293,
"children": {
"TorchPolicy.evaluate": {
"total": 109.26671879179776,
"count": 18209,
"self": 109.26671879179776
}
}
},
"workers": {
"total": 0.2588223060593009,
"count": 18209,
"self": 0.0,
"children": {
"worker_root": {
"total": 577.7845156155527,
"count": 18209,
"is_parallel": true,
"self": 249.66544489143416,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005166726186871529,
"count": 1,
"is_parallel": true,
"self": 0.0005940417759120464,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004572684410959482,
"count": 10,
"is_parallel": true,
"self": 0.004572684410959482
}
}
},
"UnityEnvironment.step": {
"total": 0.03811795823276043,
"count": 1,
"is_parallel": true,
"self": 0.001652805134654045,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006010150536894798,
"count": 1,
"is_parallel": true,
"self": 0.0006010150536894798
},
"communicator.exchange": {
"total": 0.03189110802486539,
"count": 1,
"is_parallel": true,
"self": 0.03189110802486539
},
"steps_from_proto": {
"total": 0.003973030019551516,
"count": 1,
"is_parallel": true,
"self": 0.00043610110878944397,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0035369289107620716,
"count": 10,
"is_parallel": true,
"self": 0.0035369289107620716
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 328.1190707241185,
"count": 18208,
"is_parallel": true,
"self": 26.660899868700653,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.9398321765474975,
"count": 18208,
"is_parallel": true,
"self": 6.9398321765474975
},
"communicator.exchange": {
"total": 222.17609374038875,
"count": 18208,
"is_parallel": true,
"self": 222.17609374038875
},
"steps_from_proto": {
"total": 72.3422449384816,
"count": 18208,
"is_parallel": true,
"self": 8.370397214312106,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.97184772416949,
"count": 182080,
"is_parallel": true,
"self": 63.97184772416949
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.852275252342224e-05,
"count": 1,
"self": 9.852275252342224e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 571.4133970784023,
"count": 221945,
"is_parallel": true,
"self": 4.9705481473356485,
"children": {
"process_trajectory": {
"total": 307.05522330477834,
"count": 221945,
"is_parallel": true,
"self": 305.82704373216256,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2281795726157725,
"count": 4,
"is_parallel": true,
"self": 1.2281795726157725
}
}
},
"_update_policy": {
"total": 259.38762562628835,
"count": 90,
"is_parallel": true,
"self": 81.74311861023307,
"children": {
"TorchPPOOptimizer.update": {
"total": 177.6445070160553,
"count": 4587,
"is_parallel": true,
"self": 177.6445070160553
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.18577954592183232,
"count": 1,
"self": 0.0008311928249895573,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18494835309684277,
"count": 1,
"self": 0.18494835309684277
}
}
}
}
}
}
}