|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.39619481563568115, |
|
"min": 0.39619481563568115, |
|
"max": 1.4689055681228638, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 11860.48828125, |
|
"min": 11860.48828125, |
|
"max": 44560.71875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989965.0, |
|
"min": 29993.0, |
|
"max": 989965.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989965.0, |
|
"min": 29993.0, |
|
"max": 989965.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.6354079246520996, |
|
"min": -0.11585243791341782, |
|
"max": 0.7194526195526123, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 179.82044982910156, |
|
"min": -28.03628921508789, |
|
"max": 207.92181396484375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.03358595445752144, |
|
"min": -0.007329344283789396, |
|
"max": 0.47765645384788513, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 9.5048246383667, |
|
"min": -2.0155696868896484, |
|
"max": 113.68223571777344, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06819572646885977, |
|
"min": 0.06329972434676685, |
|
"max": 0.07334274620890593, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9547401705640368, |
|
"min": 0.4922901528428146, |
|
"max": 1.0642148073261612, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.016453607275685674, |
|
"min": 0.000383299948966835, |
|
"max": 0.016453607275685674, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.23035050185959943, |
|
"min": 0.004982899336568855, |
|
"max": 0.2384712323962994, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.315340418728572e-06, |
|
"min": 7.315340418728572e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0001024147658622, |
|
"min": 0.0001024147658622, |
|
"max": 0.0037591183469605997, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.1024384142857143, |
|
"min": 0.1024384142857143, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4341378000000002, |
|
"min": 1.3886848, |
|
"max": 2.653039400000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002535975871428572, |
|
"min": 0.0002535975871428572, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0035503662200000014, |
|
"min": 0.0035503662200000014, |
|
"max": 0.12531863606000002, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.011308408342301846, |
|
"min": 0.011308408342301846, |
|
"max": 0.48652711510658264, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.1583177149295807, |
|
"min": 0.1583177149295807, |
|
"max": 3.4056897163391113, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 298.5940594059406, |
|
"min": 272.08181818181816, |
|
"max": 987.7647058823529, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30158.0, |
|
"min": 16792.0, |
|
"max": 33707.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6607559840381145, |
|
"min": -0.8710588725174174, |
|
"max": 1.709727252681147, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 166.07559840381145, |
|
"min": -26.624001689255238, |
|
"max": 188.06999779492617, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6607559840381145, |
|
"min": -0.8710588725174174, |
|
"max": 1.709727252681147, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 166.07559840381145, |
|
"min": -26.624001689255238, |
|
"max": 188.06999779492617, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.03502566572467913, |
|
"min": 0.03461679298925446, |
|
"max": 9.2144193333738, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.502566572467913, |
|
"min": 3.464585807574622, |
|
"max": 156.64512866735458, |
|
"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": "1678694939", |
|
"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=Pyramids Training --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": "1678699003" |
|
}, |
|
"total": 4063.7463600270003, |
|
"count": 1, |
|
"self": 1.8777746780006055, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.14475956899991616, |
|
"count": 1, |
|
"self": 0.14475956899991616 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 4061.72382578, |
|
"count": 1, |
|
"self": 3.131588217947865, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 5.387584284000013, |
|
"count": 1, |
|
"self": 5.387584284000013 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 4053.044260323053, |
|
"count": 64131, |
|
"self": 3.05466760121908, |
|
"children": { |
|
"env_step": { |
|
"total": 2752.2836712569588, |
|
"count": 64131, |
|
"self": 2579.320178312005, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 171.14855542691544, |
|
"count": 64131, |
|
"self": 8.877685316802172, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 162.27087011011326, |
|
"count": 62554, |
|
"self": 162.27087011011326 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.814937518038505, |
|
"count": 64131, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 4052.2576724559713, |
|
"count": 64131, |
|
"is_parallel": true, |
|
"self": 1693.5504535850164, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0032108440000229166, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0013128440000400587, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0018979999999828578, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0018979999999828578 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.1587858740001593, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007447239997873112, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.000616806000152792, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000616806000152792 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.15507623300004525, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.15507623300004525 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.002348111000173958, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005828180003391026, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0017652929998348554, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0017652929998348554 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 2358.707218870955, |
|
"count": 64130, |
|
"is_parallel": true, |
|
"self": 48.47105964390221, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 29.926909965058712, |
|
"count": 64130, |
|
"is_parallel": true, |
|
"self": 29.926909965058712 |
|
}, |
|
"communicator.exchange": { |
|
"total": 2137.0491168310086, |
|
"count": 64130, |
|
"is_parallel": true, |
|
"self": 2137.0491168310086 |
|
}, |
|
"steps_from_proto": { |
|
"total": 143.26013243098532, |
|
"count": 64130, |
|
"is_parallel": true, |
|
"self": 33.65056198498337, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 109.60957044600195, |
|
"count": 513040, |
|
"is_parallel": true, |
|
"self": 109.60957044600195 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1297.7059214648755, |
|
"count": 64131, |
|
"self": 6.017780109816158, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 197.13097583605736, |
|
"count": 64131, |
|
"self": 196.83707804705796, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.2938977889994021, |
|
"count": 2, |
|
"self": 0.2938977889994021 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1094.557165519002, |
|
"count": 458, |
|
"self": 448.0128166050333, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 646.5443489139686, |
|
"count": 22806, |
|
"self": 646.5443489139686 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.4729994290973991e-06, |
|
"count": 1, |
|
"self": 1.4729994290973991e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.16039148199979536, |
|
"count": 1, |
|
"self": 0.0036048259999006405, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.15678665599989472, |
|
"count": 1, |
|
"self": 0.15678665599989472 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |