s94lopez's picture
Second Push
daa7a12 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8681857585906982,
"min": 0.8617246747016907,
"max": 2.8711941242218018,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8862.4404296875,
"min": 7700.611328125,
"max": 30545.3828125,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499912.0,
"min": 9952.0,
"max": 499912.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499912.0,
"min": 9952.0,
"max": 499912.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 28.480539321899414,
"min": 0.06870930641889572,
"max": 28.496248245239258,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2876.534423828125,
"min": 6.6648030281066895,
"max": 2927.86083984375,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.830188679245282,
"min": 2.75,
"max": 28.163636363636364,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1475.0,
"min": 121.0,
"max": 1549.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.830188679245282,
"min": 2.75,
"max": 28.163636363636364,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1475.0,
"min": 121.0,
"max": 1549.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.04759585250490893,
"min": 0.04096470710458508,
"max": 0.05477973770620712,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.09519170500981786,
"min": 0.08192941420917016,
"max": 0.1612619695447981,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2687982366365545,
"min": 0.1750995202537845,
"max": 0.6149530507185881,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.537596473273109,
"min": 0.350199040507569,
"max": 1.8410278215127833,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.500099000000002e-06,
"min": 2.500099000000002e-06,
"max": 0.00024670000131999997,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.000198000000004e-06,
"min": 5.000198000000004e-06,
"max": 0.0006972000211200003,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.101,
"min": 0.101,
"max": 0.19867999999999997,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.202,
"min": 0.202,
"max": 0.5788800000000001,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 1.990000000000001e-05,
"min": 1.990000000000001e-05,
"max": 0.0009869320000000003,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 3.980000000000002e-05,
"min": 3.980000000000002e-05,
"max": 0.0027909120000000004,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1745188860",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1745190034"
},
"total": 1173.8106681919999,
"count": 1,
"self": 0.4365396149996741,
"children": {
"run_training.setup": {
"total": 0.02320058100008282,
"count": 1,
"self": 0.02320058100008282
},
"TrainerController.start_learning": {
"total": 1173.350927996,
"count": 1,
"self": 0.9582707039592151,
"children": {
"TrainerController._reset_env": {
"total": 3.020470119000038,
"count": 1,
"self": 3.020470119000038
},
"TrainerController.advance": {
"total": 1169.2210458940408,
"count": 45528,
"self": 0.9680215890550699,
"children": {
"env_step": {
"total": 777.1709635440084,
"count": 45528,
"self": 573.1229712800598,
"children": {
"SubprocessEnvManager._take_step": {
"total": 203.48116705397217,
"count": 45528,
"self": 3.2984373559432925,
"children": {
"TorchPolicy.evaluate": {
"total": 200.18272969802888,
"count": 45528,
"self": 200.18272969802888
}
}
},
"workers": {
"total": 0.5668252099764004,
"count": 45528,
"self": 0.0,
"children": {
"worker_root": {
"total": 1169.892334609994,
"count": 45528,
"is_parallel": true,
"self": 667.077291025972,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0054461409999930765,
"count": 1,
"is_parallel": true,
"self": 0.004014567000012903,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014315739999801735,
"count": 10,
"is_parallel": true,
"self": 0.0014315739999801735
}
}
},
"UnityEnvironment.step": {
"total": 0.033421472999975776,
"count": 1,
"is_parallel": true,
"self": 0.0005497850000892868,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038939499995649385,
"count": 1,
"is_parallel": true,
"self": 0.00038939499995649385
},
"communicator.exchange": {
"total": 0.030676989999960824,
"count": 1,
"is_parallel": true,
"self": 0.030676989999960824
},
"steps_from_proto": {
"total": 0.0018053029999691717,
"count": 1,
"is_parallel": true,
"self": 0.0003579419999368838,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014473610000322878,
"count": 10,
"is_parallel": true,
"self": 0.0014473610000322878
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 502.81504358402185,
"count": 45527,
"is_parallel": true,
"self": 23.927230637047614,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.056193737019157,
"count": 45527,
"is_parallel": true,
"self": 13.056193737019157
},
"communicator.exchange": {
"total": 388.68731416500884,
"count": 45527,
"is_parallel": true,
"self": 388.68731416500884
},
"steps_from_proto": {
"total": 77.14430504494624,
"count": 45527,
"is_parallel": true,
"self": 13.787736321055036,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.3565687238912,
"count": 455270,
"is_parallel": true,
"self": 63.3565687238912
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 391.08206076097736,
"count": 45528,
"self": 1.187493573984625,
"children": {
"process_trajectory": {
"total": 84.54256373499288,
"count": 45528,
"self": 82.82474377999313,
"children": {
"RLTrainer._checkpoint": {
"total": 1.7178199549997544,
"count": 10,
"self": 1.7178199549997544
}
}
},
"_update_policy": {
"total": 305.35200345199985,
"count": 113,
"self": 161.62613715300677,
"children": {
"TorchPPOOptimizer.update": {
"total": 143.72586629899308,
"count": 9605,
"self": 143.72586629899308
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.489998890581774e-07,
"count": 1,
"self": 8.489998890581774e-07
},
"TrainerController._save_models": {
"total": 0.15114043000016864,
"count": 1,
"self": 0.0016895950002435711,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14945083499992506,
"count": 1,
"self": 0.14945083499992506
}
}
}
}
}
}
}