|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.13757723569869995, |
|
"min": 0.13162420690059662, |
|
"max": 1.4512150287628174, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 4122.91455078125, |
|
"min": 3948.72607421875, |
|
"max": 44024.05859375, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999927.0, |
|
"min": 29952.0, |
|
"max": 2999927.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999927.0, |
|
"min": 29952.0, |
|
"max": 2999927.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.7710461020469666, |
|
"min": -0.11332686990499496, |
|
"max": 0.8763967156410217, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 229.0006866455078, |
|
"min": -27.42510223388672, |
|
"max": 272.55938720703125, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.019496850669384003, |
|
"min": -0.020744167268276215, |
|
"max": 0.4210328757762909, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 5.79056453704834, |
|
"min": -6.1195292472839355, |
|
"max": 99.7847900390625, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06981827384850095, |
|
"min": 0.06264805599944555, |
|
"max": 0.07445920039967986, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0472741077275143, |
|
"min": 0.521214402797759, |
|
"max": 1.10019036806782, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01703476079509843, |
|
"min": 0.0018405289152907476, |
|
"max": 0.01703476079509843, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2555214119264765, |
|
"min": 0.019757122454584896, |
|
"max": 0.2555214119264765, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.51487282840889e-06, |
|
"min": 1.51487282840889e-06, |
|
"max": 0.00029838354339596195, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.272309242613335e-05, |
|
"min": 2.272309242613335e-05, |
|
"max": 0.0040273603575466, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10050492444444448, |
|
"min": 0.10050492444444448, |
|
"max": 0.19946118095238097, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5075738666666672, |
|
"min": 1.3962282666666668, |
|
"max": 2.8424534, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 6.044195200000004e-05, |
|
"min": 6.044195200000004e-05, |
|
"max": 0.009946171977142856, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0009066292800000006, |
|
"min": 0.0009066292800000006, |
|
"max": 0.13426109466000002, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.007645902223885059, |
|
"min": 0.007201760541647673, |
|
"max": 0.42734295129776, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.11468853056430817, |
|
"min": 0.10082464665174484, |
|
"max": 2.991400718688965, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 221.70503597122303, |
|
"min": 206.9655172413793, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30817.0, |
|
"min": 15984.0, |
|
"max": 32654.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7068970869632736, |
|
"min": -1.0000000521540642, |
|
"max": 1.7821014323744222, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 235.55179800093174, |
|
"min": -28.434001706540585, |
|
"max": 260.7465982437134, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7068970869632736, |
|
"min": -1.0000000521540642, |
|
"max": 1.7821014323744222, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 235.55179800093174, |
|
"min": -28.434001706540585, |
|
"max": 260.7465982437134, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.01763903344608084, |
|
"min": 0.01641389403114256, |
|
"max": 9.204706648364663, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.434186615559156, |
|
"min": 2.164062650888809, |
|
"max": 147.2753063738346, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1661489166", |
|
"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": "1661495990" |
|
}, |
|
"total": 6823.469395155, |
|
"count": 1, |
|
"self": 0.4843815699996412, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.044284666000066863, |
|
"count": 1, |
|
"self": 0.044284666000066863 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 6822.940728919, |
|
"count": 1, |
|
"self": 4.245450612010245, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.714788956999996, |
|
"count": 1, |
|
"self": 10.714788956999996 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 6807.88889300099, |
|
"count": 195827, |
|
"self": 4.4968886719789225, |
|
"children": { |
|
"env_step": { |
|
"total": 4669.886134847071, |
|
"count": 195827, |
|
"self": 4350.36956031324, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 317.1994738057723, |
|
"count": 195827, |
|
"self": 13.644236579821836, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 303.55523722595046, |
|
"count": 187564, |
|
"self": 104.95797849292887, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 198.5972587330216, |
|
"count": 187564, |
|
"self": 198.5972587330216 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.317100728058449, |
|
"count": 195827, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 6811.22335971997, |
|
"count": 195827, |
|
"is_parallel": true, |
|
"self": 2774.82443109886, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005799276000061582, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0045933690001902505, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012059069998713312, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012059069998713312 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.0534858759999679, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004933599999503713, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004618530000470855, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004618530000470855 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.050939225999968585, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.050939225999968585 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015914370000018607, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00041331299996727466, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001178124000034586, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001178124000034586 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 4036.3989286211104, |
|
"count": 195826, |
|
"is_parallel": true, |
|
"self": 83.52351238140636, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 69.53496493400007, |
|
"count": 195826, |
|
"is_parallel": true, |
|
"self": 69.53496493400007 |
|
}, |
|
"communicator.exchange": { |
|
"total": 3605.7536178129876, |
|
"count": 195826, |
|
"is_parallel": true, |
|
"self": 3605.7536178129876 |
|
}, |
|
"steps_from_proto": { |
|
"total": 277.5868334927162, |
|
"count": 195826, |
|
"is_parallel": true, |
|
"self": 69.13235903333157, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 208.45447445938464, |
|
"count": 1566608, |
|
"is_parallel": true, |
|
"self": 208.45447445938464 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 2133.5058694819404, |
|
"count": 195827, |
|
"self": 8.2385836368544, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 498.3945108650953, |
|
"count": 195827, |
|
"self": 497.79671575309567, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.5977951119996305, |
|
"count": 6, |
|
"self": 0.5977951119996305 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1626.872774979991, |
|
"count": 1403, |
|
"self": 629.0669515019789, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 997.805823478012, |
|
"count": 68346, |
|
"self": 997.805823478012 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.1370002539479174e-06, |
|
"count": 1, |
|
"self": 1.1370002539479174e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.0915952120003567, |
|
"count": 1, |
|
"self": 0.0017382490004820284, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08985696299987467, |
|
"count": 1, |
|
"self": 0.08985696299987467 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |