|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.537936270236969, |
|
"min": 0.537936270236969, |
|
"max": 1.3857479095458984, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 16301.6201171875, |
|
"min": 16301.6201171875, |
|
"max": 42038.046875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989974.0, |
|
"min": 29952.0, |
|
"max": 989974.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989974.0, |
|
"min": 29952.0, |
|
"max": 989974.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.2987557351589203, |
|
"min": -0.10508545488119125, |
|
"max": 0.3129414916038513, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 77.37773895263672, |
|
"min": -25.430679321289062, |
|
"max": 80.42596435546875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.016964631155133247, |
|
"min": -0.016964631155133247, |
|
"max": 0.3806672692298889, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -4.393839359283447, |
|
"min": -4.393839359283447, |
|
"max": 90.2181396484375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06988025348853423, |
|
"min": 0.06411768943503847, |
|
"max": 0.07604630539601967, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0482038023280134, |
|
"min": 0.5323241377721377, |
|
"max": 1.0996024134733222, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.012970652159452178, |
|
"min": 0.0006412699549866713, |
|
"max": 0.014323089758630992, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.19455978239178268, |
|
"min": 0.008977779369813399, |
|
"max": 0.2005232566208339, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.422677525806665e-06, |
|
"min": 7.422677525806665e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00011134016288709997, |
|
"min": 0.00011134016288709997, |
|
"max": 0.0035084615305128993, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10247419333333334, |
|
"min": 0.10247419333333334, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5371129000000001, |
|
"min": 1.3886848, |
|
"max": 2.5694871, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.000257171914, |
|
"min": 0.000257171914, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0038575787099999997, |
|
"min": 0.0038575787099999997, |
|
"max": 0.11697176129, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.012460886500775814, |
|
"min": 0.012460886500775814, |
|
"max": 0.5152274966239929, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.18691329658031464, |
|
"min": 0.17502087354660034, |
|
"max": 3.6065926551818848, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 496.08620689655174, |
|
"min": 496.08620689655174, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28773.0, |
|
"min": 15984.0, |
|
"max": 32439.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.3372526048568256, |
|
"min": -1.0000000521540642, |
|
"max": 1.3372526048568256, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 76.22339847683907, |
|
"min": -30.469401702284813, |
|
"max": 76.22339847683907, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.3372526048568256, |
|
"min": -1.0000000521540642, |
|
"max": 1.3372526048568256, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 76.22339847683907, |
|
"min": -30.469401702284813, |
|
"max": 76.22339847683907, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.06230818303741041, |
|
"min": 0.06230818303741041, |
|
"max": 10.663450403138995, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.5515664331323933, |
|
"min": 3.5515664331323933, |
|
"max": 170.61520645022392, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1661155224", |
|
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
|
"mlagents_version": "0.29.0.dev0", |
|
"mlagents_envs_version": "0.29.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.8.1+cu102", |
|
"numpy_version": "1.21.6", |
|
"end_time_seconds": "1661158307" |
|
}, |
|
"total": 3083.676767436, |
|
"count": 1, |
|
"self": 0.6833655189998353, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.05427349999990838, |
|
"count": 1, |
|
"self": 0.05427349999990838 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 3082.939128417, |
|
"count": 1, |
|
"self": 2.4252582980629995, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 11.044875691000016, |
|
"count": 1, |
|
"self": 11.044875691000016 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 3069.361343868938, |
|
"count": 63433, |
|
"self": 2.6793028398874412, |
|
"children": { |
|
"env_step": { |
|
"total": 1802.4806044610023, |
|
"count": 63433, |
|
"self": 1658.497047256109, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 142.53790752391296, |
|
"count": 63433, |
|
"self": 7.213905162863057, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 135.3240023610499, |
|
"count": 62567, |
|
"self": 29.596378664142776, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 105.72762369690713, |
|
"count": 62567, |
|
"self": 105.72762369690713 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.4456496809802957, |
|
"count": 63433, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 3076.388358235013, |
|
"count": 63433, |
|
"is_parallel": true, |
|
"self": 1586.414721414057, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.009083742000029815, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0047278530000767205, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.004355888999953095, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.004355888999953095 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.07994424399998934, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007682590000968048, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005485279998538317, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005485279998538317 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.057014517999959935, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.057014517999959935 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.021612939000078768, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006446339996273309, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.020968305000451437, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.020968305000451437 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1489.973636820956, |
|
"count": 63432, |
|
"is_parallel": true, |
|
"self": 40.21890103792134, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 23.365737592011783, |
|
"count": 63432, |
|
"is_parallel": true, |
|
"self": 23.365737592011783 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1299.3704599559792, |
|
"count": 63432, |
|
"is_parallel": true, |
|
"self": 1299.3704599559792 |
|
}, |
|
"steps_from_proto": { |
|
"total": 127.0185382350437, |
|
"count": 63432, |
|
"is_parallel": true, |
|
"self": 34.502453151115105, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 92.5160850839286, |
|
"count": 507456, |
|
"is_parallel": true, |
|
"self": 92.5160850839286 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1264.2014365680484, |
|
"count": 63433, |
|
"self": 4.966577621054967, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 225.00560161999533, |
|
"count": 63433, |
|
"self": 224.59825272099602, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.4073488989993166, |
|
"count": 2, |
|
"self": 0.4073488989993166 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1034.229257326998, |
|
"count": 451, |
|
"self": 284.0283822679801, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 750.200875059018, |
|
"count": 22830, |
|
"self": 750.200875059018 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.2909995348309167e-06, |
|
"count": 1, |
|
"self": 1.2909995348309167e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.10764926799947716, |
|
"count": 1, |
|
"self": 0.0027385729990783148, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.10491069500039885, |
|
"count": 1, |
|
"self": 0.10491069500039885 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |