|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.5527415871620178, |
|
"min": 0.5523451566696167, |
|
"max": 1.3948736190795898, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 16502.65234375, |
|
"min": 16502.65234375, |
|
"max": 42314.88671875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989973.0, |
|
"min": 29952.0, |
|
"max": 989973.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989973.0, |
|
"min": 29952.0, |
|
"max": 989973.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.3957841694355011, |
|
"min": -0.12585315108299255, |
|
"max": 0.502660870552063, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 106.07015991210938, |
|
"min": -29.827198028564453, |
|
"max": 133.2051239013672, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.005644519813358784, |
|
"min": -0.005644519813358784, |
|
"max": 0.36706244945526123, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -1.5127313137054443, |
|
"min": -1.5127313137054443, |
|
"max": 88.09498596191406, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.0702554980123837, |
|
"min": 0.06469593176458908, |
|
"max": 0.0729148129844374, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9835769721733718, |
|
"min": 0.484229757005015, |
|
"max": 1.0290095096410654, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.012675065438694826, |
|
"min": 0.00012791870751004402, |
|
"max": 0.01446847533453347, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.17745091614172756, |
|
"min": 0.0016629431976305721, |
|
"max": 0.2025586546834686, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.456640371628568e-06, |
|
"min": 7.456640371628568e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010439296520279995, |
|
"min": 0.00010439296520279995, |
|
"max": 0.0032247235250921994, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.1024855142857143, |
|
"min": 0.1024855142857143, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4347972000000002, |
|
"min": 1.3691136000000002, |
|
"max": 2.3591479000000004, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025830287714285707, |
|
"min": 0.00025830287714285707, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0036162402799999986, |
|
"min": 0.0036162402799999986, |
|
"max": 0.10750328921999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.011794920079410076, |
|
"min": 0.011794920079410076, |
|
"max": 0.5164536833763123, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.1651288866996765, |
|
"min": 0.1651288866996765, |
|
"max": 3.615175724029541, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 462.0144927536232, |
|
"min": 393.34722222222223, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31879.0, |
|
"min": 15984.0, |
|
"max": 32409.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.422008668706901, |
|
"min": -1.0000000521540642, |
|
"max": 1.5510694250050518, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 98.11859814077616, |
|
"min": -32.000001668930054, |
|
"max": 111.67699860036373, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.422008668706901, |
|
"min": -1.0000000521540642, |
|
"max": 1.5510694250050518, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 98.11859814077616, |
|
"min": -32.000001668930054, |
|
"max": 111.67699860036373, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.05665547018735737, |
|
"min": 0.05306037882110104, |
|
"max": 10.009581180289388, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.9092274429276586, |
|
"min": 3.708133256994188, |
|
"max": 160.1532988846302, |
|
"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": "1674286409", |
|
"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": "1.21.6", |
|
"end_time_seconds": "1674288334" |
|
}, |
|
"total": 1925.7565536030002, |
|
"count": 1, |
|
"self": 0.4738183750000644, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10477953999998135, |
|
"count": 1, |
|
"self": 0.10477953999998135 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1925.177955688, |
|
"count": 1, |
|
"self": 1.1358102249316744, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 5.949775842000008, |
|
"count": 1, |
|
"self": 5.949775842000008 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1918.0104498010683, |
|
"count": 63451, |
|
"self": 1.1982808740815472, |
|
"children": { |
|
"env_step": { |
|
"total": 1287.8195038139816, |
|
"count": 63451, |
|
"self": 1189.3033069459343, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 97.79966924304858, |
|
"count": 63451, |
|
"self": 4.196630545036783, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 93.6030386980118, |
|
"count": 62548, |
|
"self": 31.541474009008084, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 62.06156468900372, |
|
"count": 62548, |
|
"self": 62.06156468900372 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.7165276249985482, |
|
"count": 63451, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1921.353110355959, |
|
"count": 63451, |
|
"is_parallel": true, |
|
"self": 823.6087845999732, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.001646513999958188, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006136999999171167, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0010328140000410713, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0010328140000410713 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05680358000006436, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004660600001216153, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004158499999675769, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004158499999675769 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05434399000000667, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05434399000000667 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015776799999684954, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003975269997908981, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011801530001775973, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011801530001775973 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1097.7443257559858, |
|
"count": 63450, |
|
"is_parallel": true, |
|
"self": 26.316004235998207, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 20.578618926014315, |
|
"count": 63450, |
|
"is_parallel": true, |
|
"self": 20.578618926014315 |
|
}, |
|
"communicator.exchange": { |
|
"total": 956.6622835870012, |
|
"count": 63450, |
|
"is_parallel": true, |
|
"self": 956.6622835870012 |
|
}, |
|
"steps_from_proto": { |
|
"total": 94.18741900697194, |
|
"count": 63450, |
|
"is_parallel": true, |
|
"self": 20.602597276971892, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 73.58482173000004, |
|
"count": 507600, |
|
"is_parallel": true, |
|
"self": 73.58482173000004 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 628.9926651130052, |
|
"count": 63451, |
|
"self": 2.094927929019377, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 136.89611436698294, |
|
"count": 63451, |
|
"self": 136.72151177498301, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.17460259199992834, |
|
"count": 2, |
|
"self": 0.17460259199992834 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 490.00162281700284, |
|
"count": 439, |
|
"self": 184.58559054199975, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 305.4160322750031, |
|
"count": 22806, |
|
"self": 305.4160322750031 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.930001058615744e-07, |
|
"count": 1, |
|
"self": 8.930001058615744e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08191892700006065, |
|
"count": 1, |
|
"self": 0.0013647910000145203, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08055413600004613, |
|
"count": 1, |
|
"self": 0.08055413600004613 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |