|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SnowballTarget.Policy.Entropy.mean": { |
|
"value": 0.8465985655784607, |
|
"min": 0.8465985655784607, |
|
"max": 2.888360023498535, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Policy.Entropy.sum": { |
|
"value": 7478.00537109375, |
|
"min": 7478.00537109375, |
|
"max": 31142.134765625, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Step.mean": { |
|
"value": 499912.0, |
|
"min": 9952.0, |
|
"max": 499912.0, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Step.sum": { |
|
"value": 499912.0, |
|
"min": 9952.0, |
|
"max": 499912.0, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 13.26048755645752, |
|
"min": 0.06346902251243591, |
|
"max": 13.3145170211792, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 1339.3092041015625, |
|
"min": 6.156495094299316, |
|
"max": 1364.9149169921875, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Policy.CuriosityValueEstimate.mean": { |
|
"value": 0.3374719023704529, |
|
"min": -0.03719322010874748, |
|
"max": 0.5572850704193115, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Policy.CuriosityValueEstimate.sum": { |
|
"value": 34.08466339111328, |
|
"min": -3.6077423095703125, |
|
"max": 56.1488151550293, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Environment.EpisodeLength.mean": { |
|
"value": 199.0, |
|
"min": 199.0, |
|
"max": 199.0, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Environment.EpisodeLength.sum": { |
|
"value": 8756.0, |
|
"min": 8756.0, |
|
"max": 10945.0, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.mean": { |
|
"value": 26.245283018867923, |
|
"min": 2.7045454545454546, |
|
"max": 26.563636363636363, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.sum": { |
|
"value": 1391.0, |
|
"min": 119.0, |
|
"max": 1461.0, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.mean": { |
|
"value": 26.245283018867923, |
|
"min": 2.7045454545454546, |
|
"max": 26.563636363636363, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.sum": { |
|
"value": 1391.0, |
|
"min": 119.0, |
|
"max": 1461.0, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Policy.CuriosityReward.mean": { |
|
"value": 0.6727214461227633, |
|
"min": 0.6657289188016545, |
|
"max": 1.6961774544282393, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Policy.CuriosityReward.sum": { |
|
"value": 35.654236644506454, |
|
"min": 30.454864636063576, |
|
"max": 93.28975999355316, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.mean": { |
|
"value": 0.03572153003284863, |
|
"min": 0.02709126802492943, |
|
"max": 0.04086239876606586, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.sum": { |
|
"value": 0.03572153003284863, |
|
"min": 0.02709126802492943, |
|
"max": 0.08172479753213172, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.mean": { |
|
"value": 0.09401289025942484, |
|
"min": 0.053612599544452896, |
|
"max": 0.16555582738735458, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.sum": { |
|
"value": 0.09401289025942484, |
|
"min": 0.053612599544452896, |
|
"max": 0.33111165477470916, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Policy.LearningRate.mean": { |
|
"value": 3.0000990000000026e-06, |
|
"min": 3.0000990000000026e-06, |
|
"max": 0.0002965152011616, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Policy.LearningRate.sum": { |
|
"value": 3.0000990000000026e-06, |
|
"min": 3.0000990000000026e-06, |
|
"max": 0.0005833152055615999, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Policy.Epsilon.mean": { |
|
"value": 0.101, |
|
"min": 0.101, |
|
"max": 0.19883840000000003, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Policy.Epsilon.sum": { |
|
"value": 0.101, |
|
"min": 0.101, |
|
"max": 0.3944384, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Policy.Beta.mean": { |
|
"value": 5.990000000000006e-05, |
|
"min": 5.990000000000006e-05, |
|
"max": 0.004942036160000001, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Policy.Beta.sum": { |
|
"value": 5.990000000000006e-05, |
|
"min": 5.990000000000006e-05, |
|
"max": 0.00972247616, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Losses.CuriosityForwardLoss.mean": { |
|
"value": 0.03243225725988547, |
|
"min": 0.03243225725988547, |
|
"max": 0.34185425169540173, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Losses.CuriosityForwardLoss.sum": { |
|
"value": 0.03243225725988547, |
|
"min": 0.03243225725988547, |
|
"max": 0.34185425169540173, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Losses.CuriosityInverseLoss.mean": { |
|
"value": 0.7320157647132873, |
|
"min": 0.7320157647132873, |
|
"max": 2.879084587097168, |
|
"count": 50 |
|
}, |
|
"SnowballTarget.Losses.CuriosityInverseLoss.sum": { |
|
"value": 0.7320157647132873, |
|
"min": 0.7320157647132873, |
|
"max": 5.579177109400431, |
|
"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 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1676556822", |
|
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", |
|
"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": "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": "1676558007" |
|
}, |
|
"total": 1185.024074343, |
|
"count": 1, |
|
"self": 0.8077287450000767, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10987415499994313, |
|
"count": 1, |
|
"self": 0.10987415499994313 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1184.106471443, |
|
"count": 1, |
|
"self": 1.793562308952005, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.182390317, |
|
"count": 1, |
|
"self": 10.182390317 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1171.9141839040478, |
|
"count": 45538, |
|
"self": 0.7986087780659545, |
|
"children": { |
|
"env_step": { |
|
"total": 1171.1155751259819, |
|
"count": 45538, |
|
"self": 788.3263637099667, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 382.0375126759848, |
|
"count": 45538, |
|
"self": 4.315550767000104, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 377.72196190898467, |
|
"count": 45538, |
|
"self": 86.51323241896353, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 291.20872949002114, |
|
"count": 45538, |
|
"self": 291.20872949002114 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.751698740030406, |
|
"count": 45538, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1179.627843267012, |
|
"count": 45538, |
|
"is_parallel": true, |
|
"self": 550.1330180550267, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.006479704000184938, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0037976429998707317, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0026820610003142065, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0026820610003142065 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05611901299994315, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00045958300006532227, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00036506099991129304, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00036506099991129304 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05340488499996354, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05340488499996354 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0018894840000029944, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005524620000869618, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013370219999160327, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0013370219999160327 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 629.4948252119852, |
|
"count": 45537, |
|
"is_parallel": true, |
|
"self": 25.075391761984292, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 14.194293234996849, |
|
"count": 45537, |
|
"is_parallel": true, |
|
"self": 14.194293234996849 |
|
}, |
|
"communicator.exchange": { |
|
"total": 504.695110424989, |
|
"count": 45537, |
|
"is_parallel": true, |
|
"self": 504.695110424989 |
|
}, |
|
"steps_from_proto": { |
|
"total": 85.53002979001508, |
|
"count": 45537, |
|
"is_parallel": true, |
|
"self": 18.75569815711947, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 66.77433163289561, |
|
"count": 455370, |
|
"is_parallel": true, |
|
"self": 66.77433163289561 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 0.0007827019999240292, |
|
"count": 1, |
|
"self": 0.0007827019999240292, |
|
"children": { |
|
"thread_root": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"trainer_advance": { |
|
"total": 1164.3029069827287, |
|
"count": 913694, |
|
"is_parallel": true, |
|
"self": 23.979679045826742, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 644.9539020549037, |
|
"count": 913694, |
|
"is_parallel": true, |
|
"self": 642.4692803469036, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 2.484621708000077, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 2.484621708000077 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 495.3693258819983, |
|
"count": 90, |
|
"is_parallel": true, |
|
"self": 194.24951560401541, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 301.1198102779829, |
|
"count": 2835, |
|
"is_parallel": true, |
|
"self": 301.1198102779829 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.21555221100015842, |
|
"count": 1, |
|
"self": 0.0012530600001809944, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.21429915099997743, |
|
"count": 1, |
|
"self": 0.21429915099997743 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |