qw132's picture
First Push
d76dc84 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9621461033821106,
"min": 0.9557538032531738,
"max": 2.851146697998047,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9144.236328125,
"min": 9144.236328125,
"max": 29104.505859375,
"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": 12.986489295959473,
"min": 0.45506078004837036,
"max": 13.022961616516113,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2532.365478515625,
"min": 88.28179168701172,
"max": 2656.68408203125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06945581830422823,
"min": 0.06218285576471549,
"max": 0.0774690392224561,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2778232732169129,
"min": 0.24873142305886195,
"max": 0.38734519611228047,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20284142860156648,
"min": 0.11553096811529066,
"max": 0.2952656197781656,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8113657144062659,
"min": 0.46212387246116265,
"max": 1.476328098890828,
"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.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": 25.15909090909091,
"min": 3.4545454545454546,
"max": 25.69090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1107.0,
"min": 152.0,
"max": 1413.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.15909090909091,
"min": 3.4545454545454546,
"max": 25.69090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1107.0,
"min": 152.0,
"max": 1413.0,
"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": "1751497024",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1751497456"
},
"total": 431.61739164799997,
"count": 1,
"self": 0.43635718799987444,
"children": {
"run_training.setup": {
"total": 0.02307214400002522,
"count": 1,
"self": 0.02307214400002522
},
"TrainerController.start_learning": {
"total": 431.15796231600007,
"count": 1,
"self": 0.3619629859992983,
"children": {
"TrainerController._reset_env": {
"total": 3.002492590999964,
"count": 1,
"self": 3.002492590999964
},
"TrainerController.advance": {
"total": 427.7120311550009,
"count": 18192,
"self": 0.38418836699452186,
"children": {
"env_step": {
"total": 307.31234996601347,
"count": 18192,
"self": 235.69077345402184,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.404350367995,
"count": 18192,
"self": 1.3123522290118217,
"children": {
"TorchPolicy.evaluate": {
"total": 70.09199813898317,
"count": 18192,
"self": 70.09199813898317
}
}
},
"workers": {
"total": 0.21722614399664053,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 429.3871189840038,
"count": 18192,
"is_parallel": true,
"self": 222.96723501402812,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0050671129999955156,
"count": 1,
"is_parallel": true,
"self": 0.003423019000365457,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016440939996300585,
"count": 10,
"is_parallel": true,
"self": 0.0016440939996300585
}
}
},
"UnityEnvironment.step": {
"total": 0.03628852499991808,
"count": 1,
"is_parallel": true,
"self": 0.0005714390001685388,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040626999998494284,
"count": 1,
"is_parallel": true,
"self": 0.00040626999998494284
},
"communicator.exchange": {
"total": 0.03348285299989584,
"count": 1,
"is_parallel": true,
"self": 0.03348285299989584
},
"steps_from_proto": {
"total": 0.0018279629998687597,
"count": 1,
"is_parallel": true,
"self": 0.00036452500057748694,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014634379992912727,
"count": 10,
"is_parallel": true,
"self": 0.0014634379992912727
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 206.41988396997567,
"count": 18191,
"is_parallel": true,
"self": 9.847617473970331,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.551273883999329,
"count": 18191,
"is_parallel": true,
"self": 5.551273883999329
},
"communicator.exchange": {
"total": 158.7279106429953,
"count": 18191,
"is_parallel": true,
"self": 158.7279106429953
},
"steps_from_proto": {
"total": 32.2930819690107,
"count": 18191,
"is_parallel": true,
"self": 5.862491251016991,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.43059071799371,
"count": 181910,
"is_parallel": true,
"self": 26.43059071799371
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.0154928219929,
"count": 18192,
"self": 0.45964784999341646,
"children": {
"process_trajectory": {
"total": 26.965859041999693,
"count": 18192,
"self": 26.56203733499933,
"children": {
"RLTrainer._checkpoint": {
"total": 0.40382170700036113,
"count": 4,
"self": 0.40382170700036113
}
}
},
"_update_policy": {
"total": 92.58998592999978,
"count": 90,
"self": 38.26358068999207,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.326405240007716,
"count": 4587,
"self": 54.326405240007716
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1679999261104967e-06,
"count": 1,
"self": 1.1679999261104967e-06
},
"TrainerController._save_models": {
"total": 0.08147441599999183,
"count": 1,
"self": 0.000825077000172314,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08064933899981952,
"count": 1,
"self": 0.08064933899981952
}
}
}
}
}
}
}