|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.08781707286834717, |
|
"min": 0.07369272410869598, |
|
"max": 1.394912600517273, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 2637.322265625, |
|
"min": 2198.990966796875, |
|
"max": 42316.0703125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989943.0, |
|
"min": 29952.0, |
|
"max": 989943.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989943.0, |
|
"min": 29952.0, |
|
"max": 989943.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.09718187898397446, |
|
"min": -0.2917120158672333, |
|
"max": -0.04798884317278862, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -23.420833587646484, |
|
"min": -69.13574981689453, |
|
"max": -11.613300323486328, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.8510758876800537, |
|
"min": 0.3720821142196655, |
|
"max": 0.9391376376152039, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 205.10928344726562, |
|
"min": 88.18346405029297, |
|
"max": 225.39303588867188, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06700153949959739, |
|
"min": 0.06474476879369935, |
|
"max": 0.07312134752079062, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9380215529943634, |
|
"min": 0.5096760511732173, |
|
"max": 1.0236988652910688, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.00291540869587073, |
|
"min": 0.0018012768567238484, |
|
"max": 0.010415353524620124, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.04081572174219022, |
|
"min": 0.021938242494536245, |
|
"max": 0.07290747467234086, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.337883268357143e-06, |
|
"min": 7.337883268357143e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.000102730365757, |
|
"min": 0.000102730365757, |
|
"max": 0.0031368230543924007, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.1024459285714286, |
|
"min": 0.1024459285714286, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4342430000000004, |
|
"min": 1.3886848, |
|
"max": 2.3591136, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002543482642857144, |
|
"min": 0.0002543482642857144, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0035608757000000013, |
|
"min": 0.0035608757000000013, |
|
"max": 0.10458619924, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.8477162718772888, |
|
"min": 0.5409694910049438, |
|
"max": 0.9265522956848145, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 11.868027687072754, |
|
"min": 4.45864725112915, |
|
"max": 12.971732139587402, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 965.8666666666667, |
|
"min": 961.6666666666666, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28976.0, |
|
"min": 15984.0, |
|
"max": 32306.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.8963034964840988, |
|
"min": -1.0000000521540642, |
|
"max": -0.7806970185854218, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -25.992801398038864, |
|
"min": -31.997201666235924, |
|
"max": -16.000000834465027, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.8963034964840988, |
|
"min": -1.0000000521540642, |
|
"max": -0.7806970185854218, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -25.992801398038864, |
|
"min": -31.997201666235924, |
|
"max": -16.000000834465027, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 8.124742853391016, |
|
"min": 5.331342129968107, |
|
"max": 11.418343337252736, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 235.61754274833947, |
|
"min": 129.06177564151585, |
|
"max": 298.34788608551025, |
|
"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": "1677075511", |
|
"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": "1677077662" |
|
}, |
|
"total": 2150.837675638, |
|
"count": 1, |
|
"self": 0.44318255600001066, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.1891178339999442, |
|
"count": 1, |
|
"self": 0.1891178339999442 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2150.205375248, |
|
"count": 1, |
|
"self": 1.4025271870632423, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.805415421999896, |
|
"count": 1, |
|
"self": 6.805415421999896 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2141.912135247937, |
|
"count": 62991, |
|
"self": 1.4459057669646427, |
|
"children": { |
|
"env_step": { |
|
"total": 1399.2863449359609, |
|
"count": 62991, |
|
"self": 1281.2017594169229, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 117.1870979979949, |
|
"count": 62991, |
|
"self": 4.7309717740211, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 112.4561262239738, |
|
"count": 62551, |
|
"self": 37.23992092392655, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 75.21620530004725, |
|
"count": 62551, |
|
"self": 75.21620530004725 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.8974875210431037, |
|
"count": 62991, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2144.866336749994, |
|
"count": 62991, |
|
"is_parallel": true, |
|
"self": 981.4654848610796, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.002791953000041758, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0009680090001893404, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0018239439998524176, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0018239439998524176 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05580563900002744, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005993500001295615, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005113400000027468, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005113400000027468 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05283338399999593, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05283338399999593 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0018615649998992012, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00046719599959033076, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013943690003088705, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013943690003088705 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1163.4008518889143, |
|
"count": 62990, |
|
"is_parallel": true, |
|
"self": 31.46124639484401, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.88197335500081, |
|
"count": 62990, |
|
"is_parallel": true, |
|
"self": 22.88197335500081 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1007.2587285750146, |
|
"count": 62990, |
|
"is_parallel": true, |
|
"self": 1007.2587285750146 |
|
}, |
|
"steps_from_proto": { |
|
"total": 101.79890356405485, |
|
"count": 62990, |
|
"is_parallel": true, |
|
"self": 23.7520151872277, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 78.04688837682716, |
|
"count": 503920, |
|
"is_parallel": true, |
|
"self": 78.04688837682716 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 741.1798845450114, |
|
"count": 62991, |
|
"self": 2.4699866320315778, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 159.7425318039759, |
|
"count": 62991, |
|
"self": 159.55782871997644, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1847030839994659, |
|
"count": 2, |
|
"self": 0.1847030839994659 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 578.9673661090039, |
|
"count": 431, |
|
"self": 222.06318065997584, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 356.9041854490281, |
|
"count": 22878, |
|
"self": 356.9041854490281 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.759998308960348e-07, |
|
"count": 1, |
|
"self": 8.759998308960348e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08529651500020918, |
|
"count": 1, |
|
"self": 0.0013502229999176052, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08394629200029158, |
|
"count": 1, |
|
"self": 0.08394629200029158 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |