|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.2454661726951599, |
|
"min": 0.2438683658838272, |
|
"max": 1.5889166593551636, |
|
"count": 46 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 7391.4775390625, |
|
"min": 7195.09228515625, |
|
"max": 48201.375, |
|
"count": 46 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 1379901.0, |
|
"min": 29910.0, |
|
"max": 1379901.0, |
|
"count": 46 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 1379901.0, |
|
"min": 29910.0, |
|
"max": 1379901.0, |
|
"count": 46 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.6779295802116394, |
|
"min": -0.09292546659708023, |
|
"max": 0.7612824440002441, |
|
"count": 46 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 193.20993041992188, |
|
"min": -22.395036697387695, |
|
"max": 227.62344360351562, |
|
"count": 46 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.06917993724346161, |
|
"min": -0.0011057952651754022, |
|
"max": 0.3723164498806, |
|
"count": 46 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 19.71628189086914, |
|
"min": -0.2941415309906006, |
|
"max": 88.23899841308594, |
|
"count": 46 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.0715606110045753, |
|
"min": 0.06373118343569027, |
|
"max": 0.07409594399810193, |
|
"count": 46 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.001848554064054, |
|
"min": 0.4595870365823242, |
|
"max": 1.0637401472389079, |
|
"count": 46 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015125273911204811, |
|
"min": 0.0010844276371333522, |
|
"max": 0.016129469255813295, |
|
"count": 46 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.21175383475686735, |
|
"min": 0.010844276371333521, |
|
"max": 0.24194203883719942, |
|
"count": 46 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.450995475551021e-06, |
|
"min": 7.450995475551021e-06, |
|
"max": 0.00029659622562438776, |
|
"count": 46 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0001043139366577143, |
|
"min": 0.0001043139366577143, |
|
"max": 0.0037952302777804277, |
|
"count": 46 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.1, |
|
"min": 0.09999999999999998, |
|
"max": 0.10000000000000002, |
|
"count": 46 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4000000000000001, |
|
"min": 0.7, |
|
"max": 1.5000000000000002, |
|
"count": 46 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002581149020408164, |
|
"min": 0.0002581149020408164, |
|
"max": 0.009886654275510205, |
|
"count": 46 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0036136086285714296, |
|
"min": 0.0036136086285714296, |
|
"max": 0.12652116375714287, |
|
"count": 46 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.010419806465506554, |
|
"min": 0.010419806465506554, |
|
"max": 0.36617204546928406, |
|
"count": 46 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.14587728679180145, |
|
"min": 0.14587728679180145, |
|
"max": 2.563204288482666, |
|
"count": 46 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 262.4824561403509, |
|
"min": 242.04132231404958, |
|
"max": 999.0, |
|
"count": 46 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29923.0, |
|
"min": 16581.0, |
|
"max": 33378.0, |
|
"count": 46 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7024122663495833, |
|
"min": -0.999962551984936, |
|
"max": 1.7566718604648486, |
|
"count": 46 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 194.0749983638525, |
|
"min": -31.998801663517952, |
|
"max": 224.85399813950062, |
|
"count": 46 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7024122663495833, |
|
"min": -0.999962551984936, |
|
"max": 1.7566718604648486, |
|
"count": 46 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 194.0749983638525, |
|
"min": -31.998801663517952, |
|
"max": 224.85399813950062, |
|
"count": 46 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.028350559796563812, |
|
"min": 0.026500153520542837, |
|
"max": 6.862230844357434, |
|
"count": 46 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.2319638168082747, |
|
"min": 3.1286544502800098, |
|
"max": 116.65792435407639, |
|
"count": 46 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 46 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 46 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1679229482", |
|
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining2 --no-graphics", |
|
"mlagents_version": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.11.0+cu102", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1679232788" |
|
}, |
|
"total": 3306.4794070059997, |
|
"count": 1, |
|
"self": 0.8367734960011148, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.17392283699882682, |
|
"count": 1, |
|
"self": 0.17392283699882682 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 3305.468710673, |
|
"count": 1, |
|
"self": 2.3896251441310596, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 7.0244827779988555, |
|
"count": 1, |
|
"self": 7.0244827779988555 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 3295.9087750568706, |
|
"count": 90145, |
|
"self": 2.4606926954766095, |
|
"children": { |
|
"env_step": { |
|
"total": 2407.1799921052516, |
|
"count": 90145, |
|
"self": 2236.1181065479086, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 169.6538362672436, |
|
"count": 90145, |
|
"self": 7.15606690705863, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 162.49776936018498, |
|
"count": 87560, |
|
"self": 162.49776936018498 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.4080492900993704, |
|
"count": 90145, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 3297.432015708957, |
|
"count": 90145, |
|
"is_parallel": true, |
|
"self": 1241.269257969976, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.002846290999514167, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0008743859980313573, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.00197190500148281, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.00197190500148281 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05124855100075365, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005672670013154857, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00048581000010017306, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00048581000010017306 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.048365937000198755, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.048365937000198755 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0018295369991392363, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00040743300087342504, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0014221039982658112, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0014221039982658112 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 2056.162757738981, |
|
"count": 90144, |
|
"is_parallel": true, |
|
"self": 46.60205633400801, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 33.657413851666206, |
|
"count": 90144, |
|
"is_parallel": true, |
|
"self": 33.657413851666206 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1838.478166507315, |
|
"count": 90144, |
|
"is_parallel": true, |
|
"self": 1838.478166507315 |
|
}, |
|
"steps_from_proto": { |
|
"total": 137.42512104599155, |
|
"count": 90144, |
|
"is_parallel": true, |
|
"self": 30.324248896702557, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 107.10087214928899, |
|
"count": 721152, |
|
"is_parallel": true, |
|
"self": 107.10087214928899 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 886.2680902561424, |
|
"count": 90145, |
|
"self": 4.6611480855317495, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 173.06847194963302, |
|
"count": 90145, |
|
"self": 172.8570300576357, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.21144189199731045, |
|
"count": 2, |
|
"self": 0.21144189199731045 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 708.5384702209776, |
|
"count": 641, |
|
"self": 447.93973490305325, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 260.59873531792437, |
|
"count": 31875, |
|
"self": 260.59873531792437 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.4360011846292764e-06, |
|
"count": 1, |
|
"self": 1.4360011846292764e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.14582625799812376, |
|
"count": 1, |
|
"self": 0.0019542619957064744, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1438719960024173, |
|
"count": 1, |
|
"self": 0.1438719960024173 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |