adutchscotsman's picture
First Push
7116d05
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.0007896423339844,
"min": 2.0007896423339844,
"max": 2.8903253078460693,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 19213.583984375,
"min": 19213.583984375,
"max": 29599.822265625,
"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": 6.583017349243164,
"min": 0.01724201627075672,
"max": 6.583017349243164,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1283.6883544921875,
"min": 3.3449511528015137,
"max": 1283.6883544921875,
"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.Environment.CumulativeReward.mean": {
"value": 17.613636363636363,
"min": 2.7954545454545454,
"max": 17.613636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 775.0,
"min": 123.0,
"max": 951.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 17.613636363636363,
"min": 2.7954545454545454,
"max": 17.613636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 775.0,
"min": 123.0,
"max": 951.0,
"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": 0.06560613295570951,
"min": 0.06392081976516113,
"max": 0.07728724567650716,
"count": 19
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.06560613295570951,
"min": 0.06392081976516113,
"max": 0.07728724567650716,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.27322604407866796,
"min": 0.09544256959183543,
"max": 0.29544951222718707,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.27322604407866796,
"min": 0.09544256959183543,
"max": 0.29544951222718707,
"count": 19
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.944099352000012e-06,
"min": 1.944099352000012e-06,
"max": 0.000283632005456,
"count": 19
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.944099352000012e-06,
"min": 1.944099352000012e-06,
"max": 0.000283632005456,
"count": 19
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10064800000000006,
"min": 0.10064800000000006,
"max": 0.19454400000000002,
"count": 19
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10064800000000006,
"min": 0.10064800000000006,
"max": 0.19454400000000002,
"count": 19
},
"SnowballTarget.Policy.Beta.mean": {
"value": 4.23352000000002e-05,
"min": 4.23352000000002e-05,
"max": 0.0047277456,
"count": 19
},
"SnowballTarget.Policy.Beta.sum": {
"value": 4.23352000000002e-05,
"min": 4.23352000000002e-05,
"max": 0.0047277456,
"count": 19
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1700826986",
"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": "1700827477"
},
"total": 491.59887766300005,
"count": 1,
"self": 0.42471903800003474,
"children": {
"run_training.setup": {
"total": 0.050323979999916446,
"count": 1,
"self": 0.050323979999916446
},
"TrainerController.start_learning": {
"total": 491.1238346450001,
"count": 1,
"self": 0.5894165789970884,
"children": {
"TrainerController._reset_env": {
"total": 9.996104625000044,
"count": 1,
"self": 9.996104625000044
},
"TrainerController.advance": {
"total": 480.444687966003,
"count": 18204,
"self": 0.25744515499889076,
"children": {
"env_step": {
"total": 480.1872428110041,
"count": 18204,
"self": 353.64013338601603,
"children": {
"SubprocessEnvManager._take_step": {
"total": 126.26024053400056,
"count": 18204,
"self": 1.3918032799952016,
"children": {
"TorchPolicy.evaluate": {
"total": 124.86843725400536,
"count": 18204,
"self": 124.86843725400536
}
}
},
"workers": {
"total": 0.28686889098753454,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 489.8359470359957,
"count": 18204,
"is_parallel": true,
"self": 249.08363321999127,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00720771400006015,
"count": 1,
"is_parallel": true,
"self": 0.004342825000094308,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0028648889999658422,
"count": 10,
"is_parallel": true,
"self": 0.0028648889999658422
}
}
},
"UnityEnvironment.step": {
"total": 0.04637301499997193,
"count": 1,
"is_parallel": true,
"self": 0.00045019399999546295,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00033653100001629355,
"count": 1,
"is_parallel": true,
"self": 0.00033653100001629355
},
"communicator.exchange": {
"total": 0.04374418599991259,
"count": 1,
"is_parallel": true,
"self": 0.04374418599991259
},
"steps_from_proto": {
"total": 0.0018421040000475841,
"count": 1,
"is_parallel": true,
"self": 0.00036808899994866806,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001474015000098916,
"count": 10,
"is_parallel": true,
"self": 0.001474015000098916
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 240.7523138160044,
"count": 18203,
"is_parallel": true,
"self": 10.373069895024628,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.316572626997527,
"count": 18203,
"is_parallel": true,
"self": 5.316572626997527
},
"communicator.exchange": {
"total": 191.79841552200332,
"count": 18203,
"is_parallel": true,
"self": 191.79841552200332
},
"steps_from_proto": {
"total": 33.264255771978924,
"count": 18203,
"is_parallel": true,
"self": 6.214291108950761,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.049964663028163,
"count": 182030,
"is_parallel": true,
"self": 27.049964663028163
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015348600004472246,
"count": 1,
"self": 0.00015348600004472246,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 475.2798268419816,
"count": 641063,
"is_parallel": true,
"self": 13.251337895023312,
"children": {
"process_trajectory": {
"total": 339.13725132395837,
"count": 641063,
"is_parallel": true,
"self": 338.66404402495834,
"children": {
"RLTrainer._checkpoint": {
"total": 0.47320729900002334,
"count": 4,
"is_parallel": true,
"self": 0.47320729900002334
}
}
},
"_update_policy": {
"total": 122.89123762299994,
"count": 19,
"is_parallel": true,
"self": 53.30067301099973,
"children": {
"TorchPPOOptimizer.update": {
"total": 69.59056461200021,
"count": 4635,
"is_parallel": true,
"self": 69.59056461200021
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09347198899990872,
"count": 1,
"self": 0.000901821000070413,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0925701679998383,
"count": 1,
"self": 0.0925701679998383
}
}
}
}
}
}
}