|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.43382328748703003, |
|
"min": 0.42433640360832214, |
|
"max": 1.4081916809082031, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 13007.7578125, |
|
"min": 12764.404296875, |
|
"max": 42718.90234375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989979.0, |
|
"min": 29908.0, |
|
"max": 989979.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989979.0, |
|
"min": 29908.0, |
|
"max": 989979.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.48680076003074646, |
|
"min": -0.08447042107582092, |
|
"max": 0.5053261518478394, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 132.8966064453125, |
|
"min": -20.357372283935547, |
|
"max": 139.975341796875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.06171848997473717, |
|
"min": -0.06171848997473717, |
|
"max": 0.49626725912094116, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -16.84914779663086, |
|
"min": -16.84914779663086, |
|
"max": 117.61534118652344, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06889210518854552, |
|
"min": 0.06420225095085692, |
|
"max": 0.07382970919003151, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9644894726396372, |
|
"min": 0.5168079643302206, |
|
"max": 1.0598438999389628, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.017081845144723957, |
|
"min": 0.00020821583668763705, |
|
"max": 0.017081845144723957, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.23914583202613537, |
|
"min": 0.0027068058769392817, |
|
"max": 0.23914583202613537, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.393126107085719e-06, |
|
"min": 7.393126107085719e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010350376549920007, |
|
"min": 0.00010350376549920007, |
|
"max": 0.0035068928310357994, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10246434285714286, |
|
"min": 0.10246434285714286, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4345008, |
|
"min": 1.3886848, |
|
"max": 2.5689641999999995, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025618785142857164, |
|
"min": 0.00025618785142857164, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003586629920000003, |
|
"min": 0.003586629920000003, |
|
"max": 0.11691952357999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.01145519595593214, |
|
"min": 0.011347301304340363, |
|
"max": 0.6522631049156189, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.1603727489709854, |
|
"min": 0.15886221826076508, |
|
"max": 4.5658416748046875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 343.59090909090907, |
|
"min": 343.59090909090907, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30236.0, |
|
"min": 16835.0, |
|
"max": 33077.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.5853608991394097, |
|
"min": -1.0000000521540642, |
|
"max": 1.5853608991394097, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 137.92639822512865, |
|
"min": -31.994401663541794, |
|
"max": 137.92639822512865, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.5853608991394097, |
|
"min": -1.0000000521540642, |
|
"max": 1.5853608991394097, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 137.92639822512865, |
|
"min": -31.994401663541794, |
|
"max": 137.92639822512865, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.04112258276801112, |
|
"min": 0.04112258276801112, |
|
"max": 13.060724968419356, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.5776647008169675, |
|
"min": 3.1772221915744012, |
|
"max": 222.03232446312904, |
|
"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": "1678055080", |
|
"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 --force", |
|
"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": "1678057334" |
|
}, |
|
"total": 2254.1776225440003, |
|
"count": 1, |
|
"self": 0.47487609000017983, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11650820800014117, |
|
"count": 1, |
|
"self": 0.11650820800014117 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2253.586238246, |
|
"count": 1, |
|
"self": 1.4222258369495648, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.508980952999991, |
|
"count": 1, |
|
"self": 6.508980952999991 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2245.5580525580494, |
|
"count": 63707, |
|
"self": 1.4705577059135067, |
|
"children": { |
|
"env_step": { |
|
"total": 1497.5796873090844, |
|
"count": 63707, |
|
"self": 1378.6119171700138, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 118.08130463908356, |
|
"count": 63707, |
|
"self": 4.980430990174227, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 113.10087364890933, |
|
"count": 62561, |
|
"self": 38.20560747484933, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 74.89526617406, |
|
"count": 62561, |
|
"self": 74.89526617406 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.8864654999870254, |
|
"count": 63707, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2248.529233110871, |
|
"count": 63707, |
|
"is_parallel": true, |
|
"self": 992.0178266518606, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0019161579998581146, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007118719995560241, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012042860003020905, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012042860003020905 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.0754035400000248, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005286109999360633, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004637070001081156, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004637070001081156 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.07282575699991867, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.07282575699991867 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015854650000619586, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003908089997821662, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011946560002797924, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011946560002797924 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1256.5114064590102, |
|
"count": 63706, |
|
"is_parallel": true, |
|
"self": 31.80658956304387, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 24.963466806902943, |
|
"count": 63706, |
|
"is_parallel": true, |
|
"self": 24.963466806902943 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1101.0636566900398, |
|
"count": 63706, |
|
"is_parallel": true, |
|
"self": 1101.0636566900398 |
|
}, |
|
"steps_from_proto": { |
|
"total": 98.67769339902361, |
|
"count": 63706, |
|
"is_parallel": true, |
|
"self": 23.860228153129356, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 74.81746524589425, |
|
"count": 509648, |
|
"is_parallel": true, |
|
"self": 74.81746524589425 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 746.5078075430515, |
|
"count": 63707, |
|
"self": 2.7304096830644085, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 168.30442408398767, |
|
"count": 63707, |
|
"self": 168.05315054798803, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.2512735359996441, |
|
"count": 2, |
|
"self": 0.2512735359996441 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 575.4729737759994, |
|
"count": 448, |
|
"self": 227.4751059150335, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 347.9978678609659, |
|
"count": 22806, |
|
"self": 347.9978678609659 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.540008250041865e-07, |
|
"count": 1, |
|
"self": 9.540008250041865e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09697794400017301, |
|
"count": 1, |
|
"self": 0.0018397260000710958, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09513821800010192, |
|
"count": 1, |
|
"self": 0.09513821800010192 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |