lbaeriswyl's picture
First Push
a62cd35 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0747202634811401,
"min": 1.0697622299194336,
"max": 2.8903579711914062,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10308.716796875,
"min": 10296.0625,
"max": 29613.673828125,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.507528305053711,
"min": -0.020696792751550674,
"max": 12.507528305053711,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2564.043212890625,
"min": -4.0151777267456055,
"max": 2564.043212890625,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.727272727272727,
"min": 2.3863636363636362,
"max": 26.295454545454547,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1415.0,
"min": 105.0,
"max": 1420.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.727272727272727,
"min": 2.3863636363636362,
"max": 26.295454545454547,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1415.0,
"min": 105.0,
"max": 1420.0,
"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
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.03377082737715682,
"min": 0.03017920497513842,
"max": 0.041207270572340346,
"count": 47
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.03377082737715682,
"min": 0.03017920497513842,
"max": 0.041207270572340346,
"count": 47
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19784099807341893,
"min": 0.07500213319583544,
"max": 0.3213471621274948,
"count": 47
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.19784099807341893,
"min": 0.07500213319583544,
"max": 0.3213471621274948,
"count": 47
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.21769826079999e-06,
"min": 5.21769826079999e-06,
"max": 0.00029345280218239997,
"count": 47
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.21769826079999e-06,
"min": 5.21769826079999e-06,
"max": 0.00029345280218239997,
"count": 47
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1017392,
"min": 0.1017392,
"max": 0.19781760000000007,
"count": 47
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.1017392,
"min": 0.1017392,
"max": 0.19781760000000007,
"count": 47
},
"SnowballTarget.Policy.Beta.mean": {
"value": 9.678607999999981e-05,
"min": 9.678607999999981e-05,
"max": 0.004891098240000002,
"count": 47
},
"SnowballTarget.Policy.Beta.sum": {
"value": 9.678607999999981e-05,
"min": 9.678607999999981e-05,
"max": 0.004891098240000002,
"count": 47
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1712005252",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=SnowballTarget2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1712006259"
},
"total": 1006.7551526090001,
"count": 1,
"self": 0.4754103750001377,
"children": {
"run_training.setup": {
"total": 0.05499911400011115,
"count": 1,
"self": 0.05499911400011115
},
"TrainerController.start_learning": {
"total": 1006.2247431199999,
"count": 1,
"self": 1.0095576380076636,
"children": {
"TrainerController._reset_env": {
"total": 1.939219668000078,
"count": 1,
"self": 1.939219668000078
},
"TrainerController.advance": {
"total": 1003.1369046829923,
"count": 45464,
"self": 1.0276376590309155,
"children": {
"env_step": {
"total": 789.5192624559918,
"count": 45464,
"self": 623.9515064660118,
"children": {
"SubprocessEnvManager._take_step": {
"total": 164.9713538080223,
"count": 45464,
"self": 3.392746150009316,
"children": {
"TorchPolicy.evaluate": {
"total": 161.57860765801297,
"count": 45464,
"self": 161.57860765801297
}
}
},
"workers": {
"total": 0.5964021819577283,
"count": 45464,
"self": 0.0,
"children": {
"worker_root": {
"total": 1002.4944070989654,
"count": 45464,
"is_parallel": true,
"self": 457.6928957929681,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002348888000142324,
"count": 1,
"is_parallel": true,
"self": 0.0007011549996605027,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016477330004818214,
"count": 10,
"is_parallel": true,
"self": 0.0016477330004818214
}
}
},
"UnityEnvironment.step": {
"total": 0.040288954000061494,
"count": 1,
"is_parallel": true,
"self": 0.000789435000569938,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00048295699980371865,
"count": 1,
"is_parallel": true,
"self": 0.00048295699980371865
},
"communicator.exchange": {
"total": 0.03684074699958728,
"count": 1,
"is_parallel": true,
"self": 0.03684074699958728
},
"steps_from_proto": {
"total": 0.002175815000100556,
"count": 1,
"is_parallel": true,
"self": 0.00041472400016573374,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017610909999348223,
"count": 10,
"is_parallel": true,
"self": 0.0017610909999348223
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 544.8015113059973,
"count": 45463,
"is_parallel": true,
"self": 26.88873167888596,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 14.982445247975647,
"count": 45463,
"is_parallel": true,
"self": 14.982445247975647
},
"communicator.exchange": {
"total": 415.06697272404836,
"count": 45463,
"is_parallel": true,
"self": 415.06697272404836
},
"steps_from_proto": {
"total": 87.86336165508737,
"count": 45463,
"is_parallel": true,
"self": 15.925444751959276,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.9379169031281,
"count": 454630,
"is_parallel": true,
"self": 71.9379169031281
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 212.59000456796957,
"count": 45464,
"self": 1.128955105949899,
"children": {
"process_trajectory": {
"total": 70.564516887021,
"count": 45464,
"self": 69.21331099902181,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3512058879991855,
"count": 10,
"self": 1.3512058879991855
}
}
},
"_update_policy": {
"total": 140.89653257499867,
"count": 47,
"self": 99.6590631869908,
"children": {
"TorchPPOOptimizer.update": {
"total": 41.23746938800787,
"count": 2856,
"self": 41.23746938800787
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.421999968442833e-06,
"count": 1,
"self": 1.421999968442833e-06
},
"TrainerController._save_models": {
"total": 0.13905970899986642,
"count": 1,
"self": 0.0013036739997005498,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13775603500016587,
"count": 1,
"self": 0.13775603500016587
}
}
}
}
}
}
}