|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.9002475142478943, |
|
"min": 0.9002475142478943, |
|
"max": 1.4464631080627441, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 26964.212890625, |
|
"min": 26964.212890625, |
|
"max": 43879.90625, |
|
"count": 3 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 89950.0, |
|
"min": 29914.0, |
|
"max": 89950.0, |
|
"count": 3 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 89950.0, |
|
"min": 29914.0, |
|
"max": 89950.0, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.11576081067323685, |
|
"min": -0.11576081067323685, |
|
"max": -0.04533236473798752, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -27.89835548400879, |
|
"min": -27.89835548400879, |
|
"max": -10.743770599365234, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.21440313756465912, |
|
"min": 0.21440313756465912, |
|
"max": 0.513836681842804, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 51.67115783691406, |
|
"min": 51.67115783691406, |
|
"max": 121.77928924560547, |
|
"count": 3 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06792673453281413, |
|
"min": 0.06688502743784329, |
|
"max": 0.0750250406942492, |
|
"count": 3 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.8151208143937695, |
|
"min": 0.5251752848597444, |
|
"max": 0.8151208143937695, |
|
"count": 3 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.0020234268812053574, |
|
"min": 0.0015720525543998032, |
|
"max": 0.010603704389636514, |
|
"count": 3 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.024281122574464287, |
|
"min": 0.017292578098397834, |
|
"max": 0.0742259307274556, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.689132436958332e-05, |
|
"min": 7.689132436958332e-05, |
|
"max": 0.00025234544445628564, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0009226958924349999, |
|
"min": 0.0009226958924349999, |
|
"max": 0.0018351184882939998, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.12563041666666666, |
|
"min": 0.12563041666666666, |
|
"max": 0.18411514285714287, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5075649999999998, |
|
"min": 1.2888060000000001, |
|
"max": 1.7117060000000002, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0025704786250000003, |
|
"min": 0.0025704786250000003, |
|
"max": 0.00841310277142857, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0308457435, |
|
"min": 0.0308457435, |
|
"max": 0.061219429400000004, |
|
"count": 3 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.148046612739563, |
|
"min": 0.148046612739563, |
|
"max": 0.5210483074188232, |
|
"count": 3 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 1.7765593528747559, |
|
"min": 1.7765593528747559, |
|
"max": 3.6473381519317627, |
|
"count": 3 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 959.2058823529412, |
|
"min": 959.2058823529412, |
|
"max": 984.1212121212121, |
|
"count": 3 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 32613.0, |
|
"min": 16713.0, |
|
"max": 32613.0, |
|
"count": 3 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.783582404255867, |
|
"min": -0.9244545989415862, |
|
"max": -0.783582404255867, |
|
"count": 3 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -26.641801744699478, |
|
"min": -30.507001765072346, |
|
"max": -14.729000851511955, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.783582404255867, |
|
"min": -0.9244545989415862, |
|
"max": -0.783582404255867, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -26.641801744699478, |
|
"min": -30.507001765072346, |
|
"max": -14.729000851511955, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 1.5969333990531809, |
|
"min": 1.5969333990531809, |
|
"max": 10.233941286802292, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 54.29573556780815, |
|
"min": 54.29573556780815, |
|
"max": 173.97700187563896, |
|
"count": 3 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 3 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 3 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1680895200", |
|
"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": "1680895388" |
|
}, |
|
"total": 187.4292282260003, |
|
"count": 1, |
|
"self": 0.5375493910005389, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10638402099993982, |
|
"count": 1, |
|
"self": 0.10638402099993982 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 186.78529481399983, |
|
"count": 1, |
|
"self": 0.12085031800415891, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 3.8885022450003817, |
|
"count": 1, |
|
"self": 3.8885022450003817 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 182.6674779099949, |
|
"count": 6351, |
|
"self": 0.12877401593050308, |
|
"children": { |
|
"env_step": { |
|
"total": 123.69153812105014, |
|
"count": 6351, |
|
"self": 113.51613997209279, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 10.09966360096314, |
|
"count": 6351, |
|
"self": 0.45030408598813665, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 9.649359514975004, |
|
"count": 6337, |
|
"self": 9.649359514975004 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.07573454799421597, |
|
"count": 6351, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 186.367601515999, |
|
"count": 6351, |
|
"is_parallel": true, |
|
"self": 82.91905703000066, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0017026460000124644, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005141149995324668, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011885310004799976, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011885310004799976 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05925974999991013, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006545579999510664, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004705720002675662, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004705720002675662 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.056530142999690725, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.056530142999690725 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016044770000007702, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00034225099989271257, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012622260001080576, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012622260001080576 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 103.44854448599835, |
|
"count": 6350, |
|
"is_parallel": true, |
|
"self": 3.1134070089838133, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 2.2349293579918594, |
|
"count": 6350, |
|
"is_parallel": true, |
|
"self": 2.2349293579918594 |
|
}, |
|
"communicator.exchange": { |
|
"total": 89.19897455601858, |
|
"count": 6350, |
|
"is_parallel": true, |
|
"self": 89.19897455601858 |
|
}, |
|
"steps_from_proto": { |
|
"total": 8.901233563004098, |
|
"count": 6350, |
|
"is_parallel": true, |
|
"self": 1.832754530967577, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 7.068479032036521, |
|
"count": 50800, |
|
"is_parallel": true, |
|
"self": 7.068479032036521 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 58.84716577301424, |
|
"count": 6351, |
|
"self": 0.16444860096999037, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 9.867070848045842, |
|
"count": 6351, |
|
"self": 9.867070848045842 |
|
}, |
|
"_update_policy": { |
|
"total": 48.81564632399841, |
|
"count": 35, |
|
"self": 31.210866144009742, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 17.604780179988666, |
|
"count": 2310, |
|
"self": 17.604780179988666 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.619999789516442e-07, |
|
"count": 1, |
|
"self": 8.619999789516442e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.1084634790004202, |
|
"count": 1, |
|
"self": 0.0016490660009367275, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.10681441299948347, |
|
"count": 1, |
|
"self": 0.10681441299948347 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |