magooie's picture
First Push
8f638de
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.5423059463500977,
"min": 0.5416013598442078,
"max": 2.8720340728759766,
"count": 100
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5160.041015625,
"min": 5160.041015625,
"max": 29412.5,
"count": 100
},
"SnowballTarget.Step.mean": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Step.sum": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.149301528930664,
"min": 0.3688669502735138,
"max": 14.149301528930664,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2759.11376953125,
"min": 71.56018829345703,
"max": 2887.493896484375,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06669108214498241,
"min": 0.06054223438881237,
"max": 0.07775944355172197,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26676432857992965,
"min": 0.24216893755524949,
"max": 0.3767527579975471,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.14995726486485378,
"min": 0.11738522801155626,
"max": 0.2709570104000615,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.5998290594594151,
"min": 0.46954091204622506,
"max": 1.3547850520003075,
"count": 100
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.3764995412000027e-06,
"min": 1.3764995412000027e-06,
"max": 0.0002983764005411999,
"count": 100
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.505998164800011e-06,
"min": 5.505998164800011e-06,
"max": 0.001477032007656,
"count": 100
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10045880000000001,
"min": 0.10045880000000001,
"max": 0.1994588,
"count": 100
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40183520000000006,
"min": 0.40183520000000006,
"max": 0.992344,
"count": 100
},
"SnowballTarget.Policy.Beta.mean": {
"value": 3.289412000000004e-05,
"min": 3.289412000000004e-05,
"max": 0.00497299412,
"count": 100
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00013157648000000017,
"min": 0.00013157648000000017,
"max": 0.0246179656,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 28.066666666666666,
"min": 3.522727272727273,
"max": 28.066666666666666,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1263.0,
"min": 155.0,
"max": 1528.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 28.066666666666666,
"min": 3.522727272727273,
"max": 28.066666666666666,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1263.0,
"min": 155.0,
"max": 1528.0,
"count": 100
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1699998389",
"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": "1700000832"
},
"total": 2442.660990272,
"count": 1,
"self": 0.7545073729997966,
"children": {
"run_training.setup": {
"total": 0.07027710100001627,
"count": 1,
"self": 0.07027710100001627
},
"TrainerController.start_learning": {
"total": 2441.8362057980003,
"count": 1,
"self": 2.8656853739994403,
"children": {
"TrainerController._reset_env": {
"total": 8.895498930000002,
"count": 1,
"self": 8.895498930000002
},
"TrainerController.advance": {
"total": 2429.947886861001,
"count": 90953,
"self": 1.42555898897308,
"children": {
"env_step": {
"total": 2428.5223278720277,
"count": 90953,
"self": 1680.5326889899775,
"children": {
"SubprocessEnvManager._take_step": {
"total": 746.4960641010633,
"count": 90953,
"self": 7.548378035039718,
"children": {
"TorchPolicy.evaluate": {
"total": 738.9476860660236,
"count": 90953,
"self": 738.9476860660236
}
}
},
"workers": {
"total": 1.4935747809868758,
"count": 90953,
"self": 0.0,
"children": {
"worker_root": {
"total": 2434.9722145600294,
"count": 90953,
"is_parallel": true,
"self": 1170.2412912800362,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006151380000005702,
"count": 1,
"is_parallel": true,
"self": 0.0037618270000621123,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023895529999435894,
"count": 10,
"is_parallel": true,
"self": 0.0023895529999435894
}
}
},
"UnityEnvironment.step": {
"total": 0.048731225999972594,
"count": 1,
"is_parallel": true,
"self": 0.0006439509999722759,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044756400001233487,
"count": 1,
"is_parallel": true,
"self": 0.00044756400001233487
},
"communicator.exchange": {
"total": 0.04562916599999767,
"count": 1,
"is_parallel": true,
"self": 0.04562916599999767
},
"steps_from_proto": {
"total": 0.0020105449999903158,
"count": 1,
"is_parallel": true,
"self": 0.00038000299997520415,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016305420000151116,
"count": 10,
"is_parallel": true,
"self": 0.0016305420000151116
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1264.7309232799932,
"count": 90952,
"is_parallel": true,
"self": 55.23839576297314,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 28.725080842955663,
"count": 90952,
"is_parallel": true,
"self": 28.725080842955663
},
"communicator.exchange": {
"total": 997.751137457021,
"count": 90952,
"is_parallel": true,
"self": 997.751137457021
},
"steps_from_proto": {
"total": 183.0163092170435,
"count": 90952,
"is_parallel": true,
"self": 34.68643904404371,
"children": {
"_process_rank_one_or_two_observation": {
"total": 148.3298701729998,
"count": 909520,
"is_parallel": true,
"self": 148.3298701729998
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00028349800004434655,
"count": 1,
"self": 0.00028349800004434655,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 2408.762618334983,
"count": 2498499,
"is_parallel": true,
"self": 55.064793560212365,
"children": {
"process_trajectory": {
"total": 1350.9754854357734,
"count": 2498499,
"is_parallel": true,
"self": 1347.0827636617735,
"children": {
"RLTrainer._checkpoint": {
"total": 3.8927217739999946,
"count": 20,
"is_parallel": true,
"self": 3.8927217739999946
}
}
},
"_update_policy": {
"total": 1002.7223393389972,
"count": 454,
"is_parallel": true,
"self": 340.2443615860077,
"children": {
"TorchPPOOptimizer.update": {
"total": 662.4779777529895,
"count": 23148,
"is_parallel": true,
"self": 662.4779777529895
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1268511349999244,
"count": 1,
"self": 0.001131758000155969,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12571937699976843,
"count": 1,
"self": 0.12571937699976843
}
}
}
}
}
}
}