lesliebinbin's picture
First training of SnowballTarget
7b590a2 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.9758706092834473,
"min": 1.9758706092834473,
"max": 2.8903441429138184,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 18778.673828125,
"min": 18778.673828125,
"max": 29634.0703125,
"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": 5.395683765411377,
"min": 0.1865578293800354,
"max": 5.395683765411377,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1052.1583251953125,
"min": 36.19221878051758,
"max": 1054.10791015625,
"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.Environment.CumulativeReward.mean": {
"value": 14.045454545454545,
"min": 2.6363636363636362,
"max": 14.045454545454545,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 618.0,
"min": 139.0,
"max": 751.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 14.045454545454545,
"min": 2.6363636363636362,
"max": 14.045454545454545,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 618.0,
"min": 139.0,
"max": 751.0,
"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
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.02417615052933494,
"min": 0.018906606978271158,
"max": 0.032722449221182615,
"count": 19
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.02417615052933494,
"min": 0.018906606978271158,
"max": 0.032722449221182615,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.3594531367222468,
"min": 0.08951345160603523,
"max": 0.3594531367222468,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.3594531367222468,
"min": 0.08951345160603523,
"max": 0.3594531367222468,
"count": 19
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.9440993520000114e-06,
"min": 1.9440993520000114e-06,
"max": 0.00028363200545599993,
"count": 19
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.9440993520000114e-06,
"min": 1.9440993520000114e-06,
"max": 0.00028363200545599993,
"count": 19
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10064800000000003,
"min": 0.10064800000000003,
"max": 0.19454399999999994,
"count": 19
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10064800000000003,
"min": 0.10064800000000003,
"max": 0.19454399999999994,
"count": 19
},
"SnowballTarget.Policy.Beta.mean": {
"value": 4.2335200000000204e-05,
"min": 4.2335200000000204e-05,
"max": 0.0047277456,
"count": 19
},
"SnowballTarget.Policy.Beta.sum": {
"value": 4.2335200000000204e-05,
"min": 4.2335200000000204e-05,
"max": 0.0047277456,
"count": 19
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1778082371",
"python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]",
"command_line_arguments": "/home/lesliebinbin/codings/ml-agents/.venv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1778082682"
},
"total": 310.9200458639534,
"count": 1,
"self": 0.21932479995302856,
"children": {
"run_training.setup": {
"total": 0.01584649900905788,
"count": 1,
"self": 0.01584649900905788
},
"TrainerController.start_learning": {
"total": 310.68487456499133,
"count": 1,
"self": 0.2953757271170616,
"children": {
"TrainerController._reset_env": {
"total": 1.52095451799687,
"count": 1,
"self": 1.52095451799687
},
"TrainerController.advance": {
"total": 308.80484617792536,
"count": 18192,
"self": 0.24567918642424047,
"children": {
"env_step": {
"total": 255.0635100536747,
"count": 18192,
"self": 191.42940283403732,
"children": {
"SubprocessEnvManager._take_step": {
"total": 63.451372041366994,
"count": 18192,
"self": 0.8724347226088867,
"children": {
"TorchPolicy.evaluate": {
"total": 62.57893731875811,
"count": 18192,
"self": 62.57893731875811
}
}
},
"workers": {
"total": 0.18273517827037722,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 309.8299889517948,
"count": 18192,
"is_parallel": true,
"self": 134.94842374674045,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001495501957833767,
"count": 1,
"is_parallel": true,
"self": 0.000510062905959785,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000985439051873982,
"count": 10,
"is_parallel": true,
"self": 0.000985439051873982
}
}
},
"UnityEnvironment.step": {
"total": 0.020360553986392915,
"count": 1,
"is_parallel": true,
"self": 0.00021331000607460737,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00028094497974961996,
"count": 1,
"is_parallel": true,
"self": 0.00028094497974961996
},
"communicator.exchange": {
"total": 0.019144251011312008,
"count": 1,
"is_parallel": true,
"self": 0.019144251011312008
},
"steps_from_proto": {
"total": 0.00072204798925668,
"count": 1,
"is_parallel": true,
"self": 0.0001459711929783225,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005760767962783575,
"count": 10,
"is_parallel": true,
"self": 0.0005760767962783575
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 174.88156520505436,
"count": 18191,
"is_parallel": true,
"self": 3.4740323583828285,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.9007293343311176,
"count": 18191,
"is_parallel": true,
"self": 1.9007293343311176
},
"communicator.exchange": {
"total": 159.96125370752998,
"count": 18191,
"is_parallel": true,
"self": 159.96125370752998
},
"steps_from_proto": {
"total": 9.545549804810435,
"count": 18191,
"is_parallel": true,
"self": 2.0800670023309067,
"children": {
"_process_rank_one_or_two_observation": {
"total": 7.465482802479528,
"count": 181910,
"is_parallel": true,
"self": 7.465482802479528
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 53.495656937826425,
"count": 18192,
"self": 0.34417548892088234,
"children": {
"process_trajectory": {
"total": 19.65921381674707,
"count": 18192,
"self": 19.401679914677516,
"children": {
"RLTrainer._checkpoint": {
"total": 0.25753390206955373,
"count": 4,
"self": 0.25753390206955373
}
}
},
"_update_policy": {
"total": 33.49226763215847,
"count": 19,
"self": 19.95275435736403,
"children": {
"TorchPPOOptimizer.update": {
"total": 13.539513274794444,
"count": 570,
"self": 13.539513274794444
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.739282980561256e-07,
"count": 1,
"self": 6.739282980561256e-07
},
"TrainerController._save_models": {
"total": 0.0636974680237472,
"count": 1,
"self": 0.0005844790721312165,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06311298895161599,
"count": 1,
"self": 0.06311298895161599
}
}
}
}
}
}
}