|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.6023276448249817, |
|
"min": 0.6023276448249817, |
|
"max": 1.4576289653778076, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 18012.005859375, |
|
"min": 18012.005859375, |
|
"max": 44218.6328125, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479956.0, |
|
"min": 29952.0, |
|
"max": 479956.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479956.0, |
|
"min": 29952.0, |
|
"max": 479956.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.12124181538820267, |
|
"min": -0.21579517424106598, |
|
"max": 0.12124181538820267, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 30.552936553955078, |
|
"min": -51.143455505371094, |
|
"max": 30.552936553955078, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.01537951547652483, |
|
"min": 0.01537951547652483, |
|
"max": 0.4124768078327179, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 3.875638008117676, |
|
"min": 3.875638008117676, |
|
"max": 98.99443054199219, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06902140523782306, |
|
"min": 0.06614718391422733, |
|
"max": 0.07498427351040357, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9662996733295229, |
|
"min": 0.48248141559728036, |
|
"max": 1.0627883368984377, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.00780069653003612, |
|
"min": 0.0016326368649664236, |
|
"max": 0.008853194951902484, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.10920975142050568, |
|
"min": 0.011428458054764966, |
|
"max": 0.12301220317938572, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.1245964346614286e-05, |
|
"min": 2.1245964346614286e-05, |
|
"max": 0.00029030126037577137, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0002974435008526, |
|
"min": 0.0002974435008526, |
|
"max": 0.0030857318714227993, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10708195714285716, |
|
"min": 0.10708195714285716, |
|
"max": 0.19676708571428575, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4991474000000002, |
|
"min": 1.3382272, |
|
"max": 2.4236402, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0007174875185714287, |
|
"min": 0.0007174875185714287, |
|
"max": 0.00967703186285714, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.010044825260000001, |
|
"min": 0.010044825260000001, |
|
"max": 0.10288486228, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.020496079698204994, |
|
"min": 0.020496079698204994, |
|
"max": 0.4354810416698456, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.286945104598999, |
|
"min": 0.286945104598999, |
|
"max": 3.0483672618865967, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 718.8571428571429, |
|
"min": 718.8571428571429, |
|
"max": 999.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30192.0, |
|
"min": 15984.0, |
|
"max": 32570.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 0.5560048382456709, |
|
"min": -1.0000000521540642, |
|
"max": 0.5560048382456709, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 22.79619836807251, |
|
"min": -32.000001668930054, |
|
"max": 22.79619836807251, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 0.5560048382456709, |
|
"min": -1.0000000521540642, |
|
"max": 0.5560048382456709, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 22.79619836807251, |
|
"min": -32.000001668930054, |
|
"max": 22.79619836807251, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.14927438274025917, |
|
"min": 0.14927438274025917, |
|
"max": 8.501511403359473, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 6.120249692350626, |
|
"min": 6.120249692350626, |
|
"max": 136.02418245375156, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1659923063", |
|
"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 Trainin --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": "1659924098" |
|
}, |
|
"total": 1035.039810877, |
|
"count": 1, |
|
"self": 0.4247031660004268, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.042296103999888146, |
|
"count": 1, |
|
"self": 0.042296103999888146 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1034.5728116069997, |
|
"count": 1, |
|
"self": 0.7864293940074276, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.360547316999828, |
|
"count": 1, |
|
"self": 6.360547316999828 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1027.3225122049926, |
|
"count": 31670, |
|
"self": 0.8309564180665348, |
|
"children": { |
|
"env_step": { |
|
"total": 650.7308604079471, |
|
"count": 31670, |
|
"self": 593.1542193429873, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 57.17610939896076, |
|
"count": 31670, |
|
"self": 2.412409749920471, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 54.76369964904029, |
|
"count": 31316, |
|
"self": 18.45786313907479, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 36.3058365099655, |
|
"count": 31316, |
|
"self": 36.3058365099655 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.40053166599909673, |
|
"count": 31670, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1032.3739403930117, |
|
"count": 31670, |
|
"is_parallel": true, |
|
"self": 492.91796763601906, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0019485270001950994, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007786260000557377, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011699010001393617, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011699010001393617 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.044165623000026244, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005264840001473203, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00044565999996848404, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00044565999996848404 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04160839899986968, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04160839899986968 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015850800000407617, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00041816399971139617, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011669160003293655, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011669160003293655 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 539.4559727569927, |
|
"count": 31669, |
|
"is_parallel": true, |
|
"self": 14.463819940075837, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 12.294675055989956, |
|
"count": 31669, |
|
"is_parallel": true, |
|
"self": 12.294675055989956 |
|
}, |
|
"communicator.exchange": { |
|
"total": 464.4699136579809, |
|
"count": 31669, |
|
"is_parallel": true, |
|
"self": 464.4699136579809 |
|
}, |
|
"steps_from_proto": { |
|
"total": 48.22756410294596, |
|
"count": 31669, |
|
"is_parallel": true, |
|
"self": 12.119950288085874, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 36.10761381486009, |
|
"count": 253352, |
|
"is_parallel": true, |
|
"self": 36.10761381486009 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 375.7606953789789, |
|
"count": 31670, |
|
"self": 1.4143007069926625, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 84.03848193298563, |
|
"count": 31670, |
|
"self": 83.92844966898565, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11003226399998312, |
|
"count": 1, |
|
"self": 0.11003226399998312 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 290.3079127390006, |
|
"count": 215, |
|
"self": 113.97611269901677, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 176.33180003998382, |
|
"count": 11448, |
|
"self": 176.33180003998382 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.1509996511449572e-06, |
|
"count": 1, |
|
"self": 1.1509996511449572e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.10332154000025184, |
|
"count": 1, |
|
"self": 0.001750825000272016, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.10157071499997983, |
|
"count": 1, |
|
"self": 0.10157071499997983 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |