|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.29072749614715576, |
|
"min": 0.29072749614715576, |
|
"max": 1.4951927661895752, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 8726.4765625, |
|
"min": 8726.4765625, |
|
"max": 45358.16796875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989892.0, |
|
"min": 29952.0, |
|
"max": 989892.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989892.0, |
|
"min": 29952.0, |
|
"max": 989892.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.6439411640167236, |
|
"min": -0.06369099020957947, |
|
"max": 0.6470605731010437, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 183.52322387695312, |
|
"min": -15.349529266357422, |
|
"max": 186.03231811523438, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.015542110428214073, |
|
"min": 0.006857508327811956, |
|
"max": 0.6953685879707336, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.429501533508301, |
|
"min": 1.8240971565246582, |
|
"max": 164.80235290527344, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06894711390616269, |
|
"min": 0.0626856805583451, |
|
"max": 0.07447200964843695, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0342067085924405, |
|
"min": 0.5051136415270451, |
|
"max": 1.0342067085924405, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01580863986681733, |
|
"min": 0.0012816414478899957, |
|
"max": 0.03134790837119413, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2371295980022599, |
|
"min": 0.014098055926789952, |
|
"max": 0.2371295980022599, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.563937478719999e-06, |
|
"min": 7.563937478719999e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00011345906218079998, |
|
"min": 0.00011345906218079998, |
|
"max": 0.0035083916305361997, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10252128, |
|
"min": 0.10252128, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5378192000000002, |
|
"min": 1.3886848, |
|
"max": 2.5694638000000003, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00026187587199999994, |
|
"min": 0.00026187587199999994, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003928138079999999, |
|
"min": 0.003928138079999999, |
|
"max": 0.11696943362000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.013912472873926163, |
|
"min": 0.013744129799306393, |
|
"max": 0.862118661403656, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.20868709683418274, |
|
"min": 0.19241781532764435, |
|
"max": 6.034830570220947, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 288.92, |
|
"min": 288.92, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28892.0, |
|
"min": 15984.0, |
|
"max": 33184.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6298098856269723, |
|
"min": -1.0000000521540642, |
|
"max": 1.6898601862412055, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 164.6107984483242, |
|
"min": -30.6140016913414, |
|
"max": 174.05559918284416, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6298098856269723, |
|
"min": -1.0000000521540642, |
|
"max": 1.6898601862412055, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 164.6107984483242, |
|
"min": -30.6140016913414, |
|
"max": 174.05559918284416, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.0420838846164608, |
|
"min": 0.041843515153343516, |
|
"max": 19.943316236138344, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.250472346262541, |
|
"min": 4.100664485027664, |
|
"max": 319.0930597782135, |
|
"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": "1677662289", |
|
"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/PyramidsRND.yaml --env=./training-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": "1.22.4", |
|
"end_time_seconds": "1677664952" |
|
}, |
|
"total": 2663.6235154530004, |
|
"count": 1, |
|
"self": 0.5290401610009212, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11817966000012348, |
|
"count": 1, |
|
"self": 0.11817966000012348 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2662.9762956319996, |
|
"count": 1, |
|
"self": 1.722584907010969, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.77112106200002, |
|
"count": 1, |
|
"self": 6.77112106200002 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2654.388416355989, |
|
"count": 64201, |
|
"self": 1.8328471559657373, |
|
"children": { |
|
"env_step": { |
|
"total": 1840.2104138179914, |
|
"count": 64201, |
|
"self": 1702.3533328250414, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 136.77865119900935, |
|
"count": 64201, |
|
"self": 5.676702796891277, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 131.10194840211807, |
|
"count": 62558, |
|
"self": 44.50956117210967, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 86.5923872300084, |
|
"count": 62558, |
|
"self": 86.5923872300084 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.078429793940586, |
|
"count": 64201, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2656.497023960095, |
|
"count": 64201, |
|
"is_parallel": true, |
|
"self": 1095.9000894260053, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.002224822000016502, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0008267740004157531, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013980479996007489, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013980479996007489 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.11684680999996999, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000620659999867712, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005241660001047421, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005241660001047421 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.1139112490000116, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.1139112490000116 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017907349999859434, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004665310000291356, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013242039999568078, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013242039999568078 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1560.5969345340895, |
|
"count": 64200, |
|
"is_parallel": true, |
|
"self": 34.5413454740019, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 27.303958291069193, |
|
"count": 64200, |
|
"is_parallel": true, |
|
"self": 27.303958291069193 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1389.5862245880483, |
|
"count": 64200, |
|
"is_parallel": true, |
|
"self": 1389.5862245880483 |
|
}, |
|
"steps_from_proto": { |
|
"total": 109.1654061809702, |
|
"count": 64200, |
|
"is_parallel": true, |
|
"self": 27.336696437976343, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 81.82870974299385, |
|
"count": 513600, |
|
"is_parallel": true, |
|
"self": 81.82870974299385 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 812.3451553820319, |
|
"count": 64201, |
|
"self": 3.106659349944948, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 185.66395454109306, |
|
"count": 64201, |
|
"self": 185.45556024609368, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.20839429499937978, |
|
"count": 2, |
|
"self": 0.20839429499937978 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 623.5745414909939, |
|
"count": 453, |
|
"self": 241.95070645702435, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 381.6238350339695, |
|
"count": 22764, |
|
"self": 381.6238350339695 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0570001904852688e-06, |
|
"count": 1, |
|
"self": 1.0570001904852688e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09417224999924656, |
|
"count": 1, |
|
"self": 0.0019485519997033407, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09222369799954322, |
|
"count": 1, |
|
"self": 0.09222369799954322 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |