|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.14913859963417053, |
|
"min": 0.14280986785888672, |
|
"max": 1.4972037076950073, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 4483.70263671875, |
|
"min": 4263.7314453125, |
|
"max": 45419.171875, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999911.0, |
|
"min": 29952.0, |
|
"max": 2999911.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999911.0, |
|
"min": 29952.0, |
|
"max": 2999911.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.8364439606666565, |
|
"min": -0.12928248941898346, |
|
"max": 0.8995176553726196, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 250.09674072265625, |
|
"min": -30.639949798583984, |
|
"max": 282.44854736328125, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.015490890480577946, |
|
"min": -0.007013414986431599, |
|
"max": 0.24986021220684052, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.631776332855225, |
|
"min": -2.026876926422119, |
|
"max": 59.96644973754883, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06815431118870731, |
|
"min": 0.06460617085488667, |
|
"max": 0.0745731336345077, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9541603566419022, |
|
"min": 0.47180979958589553, |
|
"max": 1.084243738966738, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.014745534119789402, |
|
"min": 0.0009033732221130707, |
|
"max": 0.016589064211335165, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.20643747767705162, |
|
"min": 0.009253865308939315, |
|
"max": 0.24564804668383053, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.5602423370952388e-06, |
|
"min": 1.5602423370952388e-06, |
|
"max": 0.00029838354339596195, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.184339271933334e-05, |
|
"min": 2.184339271933334e-05, |
|
"max": 0.003892685702438166, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10052004761904763, |
|
"min": 0.10052004761904763, |
|
"max": 0.19946118095238097, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4072806666666668, |
|
"min": 1.3897045333333333, |
|
"max": 2.7975618333333334, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 6.195275714285716e-05, |
|
"min": 6.195275714285716e-05, |
|
"max": 0.009946171977142856, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008673386000000003, |
|
"min": 0.0008673386000000003, |
|
"max": 0.12977642714999998, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.006220940966159105, |
|
"min": 0.005891887005418539, |
|
"max": 0.34342116117477417, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.08709317445755005, |
|
"min": 0.08248642086982727, |
|
"max": 2.4039480686187744, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 223.09230769230768, |
|
"min": 196.44827586206895, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29002.0, |
|
"min": 15984.0, |
|
"max": 33922.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7769076789800937, |
|
"min": -1.0000000521540642, |
|
"max": 1.8036666600447562, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 230.99799826741219, |
|
"min": -32.000001668930054, |
|
"max": 271.1799980700016, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7769076789800937, |
|
"min": -1.0000000521540642, |
|
"max": 1.8036666600447562, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 230.99799826741219, |
|
"min": -32.000001668930054, |
|
"max": 271.1799980700016, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.01449987450667742, |
|
"min": 0.012449951865126726, |
|
"max": 6.813479390926659, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 1.8849836858680646, |
|
"min": 1.772868654166814, |
|
"max": 109.01567025482655, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1691248856", |
|
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", |
|
"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": "1691256433" |
|
}, |
|
"total": 7576.71882066, |
|
"count": 1, |
|
"self": 1.1820925519987213, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.03936663000013141, |
|
"count": 1, |
|
"self": 0.03936663000013141 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 7575.497361478001, |
|
"count": 1, |
|
"self": 4.503606413696616, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.668299003000129, |
|
"count": 1, |
|
"self": 4.668299003000129 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 7566.171914462304, |
|
"count": 195631, |
|
"self": 4.307296058438624, |
|
"children": { |
|
"env_step": { |
|
"total": 5592.913892864999, |
|
"count": 195631, |
|
"self": 5254.679443548071, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 335.6397783320149, |
|
"count": 195631, |
|
"self": 14.288204375042824, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 321.35157395697206, |
|
"count": 187567, |
|
"self": 321.35157395697206 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.594670984913364, |
|
"count": 195631, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 7558.32594025892, |
|
"count": 195631, |
|
"is_parallel": true, |
|
"self": 2658.466923565831, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0017639319999034342, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005390020000959339, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012249299998075003, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012249299998075003 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.08109298900012618, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006367080000018177, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004789150000306108, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004789150000306108 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.07807604499998888, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.07807604499998888 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001901321000104872, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003484959997877013, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0015528250003171706, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0015528250003171706 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 4899.859016693089, |
|
"count": 195630, |
|
"is_parallel": true, |
|
"self": 104.4092302853669, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 70.82726288390086, |
|
"count": 195630, |
|
"is_parallel": true, |
|
"self": 70.82726288390086 |
|
}, |
|
"communicator.exchange": { |
|
"total": 4403.381817338458, |
|
"count": 195630, |
|
"is_parallel": true, |
|
"self": 4403.381817338458 |
|
}, |
|
"steps_from_proto": { |
|
"total": 321.24070618536325, |
|
"count": 195630, |
|
"is_parallel": true, |
|
"self": 63.285251806743645, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 257.9554543786196, |
|
"count": 1565040, |
|
"is_parallel": true, |
|
"self": 257.9554543786196 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1968.9507255388664, |
|
"count": 195631, |
|
"self": 8.580396042905932, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 340.36886871795946, |
|
"count": 195631, |
|
"self": 339.6734466259584, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.6954220920010812, |
|
"count": 6, |
|
"self": 0.6954220920010812 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1620.001460778001, |
|
"count": 1392, |
|
"self": 1043.9505421059844, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 576.0509186720167, |
|
"count": 68370, |
|
"self": 576.0509186720167 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.6930007404880598e-06, |
|
"count": 1, |
|
"self": 1.6930007404880598e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.15353990599942335, |
|
"count": 1, |
|
"self": 0.0020068629983143182, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.15153304300110904, |
|
"count": 1, |
|
"self": 0.15153304300110904 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |