|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.6814805865287781, |
|
"min": 0.6814805865287781, |
|
"max": 1.4850929975509644, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 20488.033203125, |
|
"min": 20488.033203125, |
|
"max": 45051.78125, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479875.0, |
|
"min": 29952.0, |
|
"max": 479875.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479875.0, |
|
"min": 29952.0, |
|
"max": 479875.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.045080170035362244, |
|
"min": -0.10816176980733871, |
|
"max": -0.03568851947784424, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -10.864320755004883, |
|
"min": -26.066986083984375, |
|
"max": -8.600933074951172, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.029479920864105225, |
|
"min": 0.023413460701704025, |
|
"max": 0.2994338870048523, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 7.104660987854004, |
|
"min": 5.666057586669922, |
|
"max": 72.16356658935547, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06587802681254082, |
|
"min": 0.0653400118763451, |
|
"max": 0.07046575784347063, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9222923753755715, |
|
"min": 0.48918454329203553, |
|
"max": 0.9795028067711599, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.002382586146110662, |
|
"min": 0.000504094073544682, |
|
"max": 0.007526313658722016, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.03335620604554927, |
|
"min": 0.006754790995297231, |
|
"max": 0.05268419561105411, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.090657874545714e-05, |
|
"min": 2.090657874545714e-05, |
|
"max": 0.00029030126037577137, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00029269210243639996, |
|
"min": 0.00029269210243639996, |
|
"max": 0.0030861782712740004, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10696882857142855, |
|
"min": 0.10696882857142855, |
|
"max": 0.19676708571428575, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4975635999999997, |
|
"min": 1.3773696000000002, |
|
"max": 2.4216144000000006, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0007061859742857142, |
|
"min": 0.0007061859742857142, |
|
"max": 0.00967703186285714, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.009886603639999998, |
|
"min": 0.009886603639999998, |
|
"max": 0.1028997274, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.02765846438705921, |
|
"min": 0.02765846438705921, |
|
"max": 0.4789149761199951, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.38721850514411926, |
|
"min": 0.38721850514411926, |
|
"max": 3.352404832839966, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 957.75, |
|
"min": 890.59375, |
|
"max": 999.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30648.0, |
|
"min": 15984.0, |
|
"max": 33030.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.6457062971312553, |
|
"min": -1.0000000521540642, |
|
"max": -0.5161562939174473, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -20.66260150820017, |
|
"min": -30.99780160188675, |
|
"max": -16.000000834465027, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.6457062971312553, |
|
"min": -1.0000000521540642, |
|
"max": -0.5161562939174473, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -20.66260150820017, |
|
"min": -30.99780160188675, |
|
"max": -16.000000834465027, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.2787142215529457, |
|
"min": 0.27324147342005745, |
|
"max": 9.378328928723931, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 8.918855089694262, |
|
"min": 8.743727149441838, |
|
"max": 150.0532628595829, |
|
"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": "1658690199", |
|
"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 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": "1658691129" |
|
}, |
|
"total": 930.0871262540002, |
|
"count": 1, |
|
"self": 0.43164670800024396, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.051727468000024146, |
|
"count": 1, |
|
"self": 0.051727468000024146 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 929.6037520779998, |
|
"count": 1, |
|
"self": 0.6131451410360569, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 9.490488287000005, |
|
"count": 1, |
|
"self": 9.490488287000005 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 919.4071623769636, |
|
"count": 31568, |
|
"self": 0.6765168529260563, |
|
"children": { |
|
"env_step": { |
|
"total": 572.3134228350104, |
|
"count": 31568, |
|
"self": 520.3214866280291, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 51.658062212003586, |
|
"count": 31568, |
|
"self": 2.223622319994206, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 49.43443989200938, |
|
"count": 31311, |
|
"self": 16.884273461014004, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 32.550166430995375, |
|
"count": 31311, |
|
"self": 32.550166430995375 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.33387399497780734, |
|
"count": 31568, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 927.616750290009, |
|
"count": 31568, |
|
"is_parallel": true, |
|
"self": 455.0380611620097, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0048176139999895895, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0035570970000549096, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.00126051699993468, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.00126051699993468 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04821678600001178, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005084930000407439, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00048033999996732746, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00048033999996732746 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04563173000002507, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04563173000002507 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001596222999978636, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004162109999583663, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011800120000202696, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011800120000202696 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 472.5786891279993, |
|
"count": 31567, |
|
"is_parallel": true, |
|
"self": 13.265336075029268, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 11.092719159006549, |
|
"count": 31567, |
|
"is_parallel": true, |
|
"self": 11.092719159006549 |
|
}, |
|
"communicator.exchange": { |
|
"total": 403.3995632009728, |
|
"count": 31567, |
|
"is_parallel": true, |
|
"self": 403.3995632009728 |
|
}, |
|
"steps_from_proto": { |
|
"total": 44.8210706929907, |
|
"count": 31567, |
|
"is_parallel": true, |
|
"self": 10.954373417030695, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 33.86669727596001, |
|
"count": 252536, |
|
"is_parallel": true, |
|
"self": 33.86669727596001 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 346.417222689027, |
|
"count": 31568, |
|
"self": 1.0542259530284923, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 76.752455430998, |
|
"count": 31568, |
|
"self": 76.64718734899816, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.10526808199983861, |
|
"count": 1, |
|
"self": 0.10526808199983861 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 268.61054130500054, |
|
"count": 214, |
|
"self": 106.64977599799579, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 161.96076530700475, |
|
"count": 11394, |
|
"self": 161.96076530700475 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0450000900164014e-06, |
|
"count": 1, |
|
"self": 1.0450000900164014e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09295522800016442, |
|
"count": 1, |
|
"self": 0.0015712490003352286, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0913839789998292, |
|
"count": 1, |
|
"self": 0.0913839789998292 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |