|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.40224698185920715, |
|
"min": 0.40224698185920715, |
|
"max": 1.4440940618515015, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 12048.1015625, |
|
"min": 12048.1015625, |
|
"max": 43808.0390625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989991.0, |
|
"min": 29952.0, |
|
"max": 989991.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989991.0, |
|
"min": 29952.0, |
|
"max": 989991.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.1403101533651352, |
|
"min": -0.13922427594661713, |
|
"max": 0.1403101533651352, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 35.498470306396484, |
|
"min": -32.99615478515625, |
|
"max": 35.498470306396484, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.006773791275918484, |
|
"min": -0.003155412385240197, |
|
"max": 0.19336429238319397, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 1.7137691974639893, |
|
"min": -0.7762314677238464, |
|
"max": 46.60079574584961, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.069441738889402, |
|
"min": 0.0649410750140473, |
|
"max": 0.07404260663066427, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9721843444516279, |
|
"min": 0.4930547936041719, |
|
"max": 1.0351920670946129, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.009450458332883434, |
|
"min": 0.0005877843303807379, |
|
"max": 0.009450458332883434, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.13230641666036808, |
|
"min": 0.008228980625330331, |
|
"max": 0.13230641666036808, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.5322832035571495e-06, |
|
"min": 7.5322832035571495e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010545196484980009, |
|
"min": 0.00010545196484980009, |
|
"max": 0.0036335452888182993, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10251072857142855, |
|
"min": 0.10251072857142855, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4351501999999998, |
|
"min": 1.3886848, |
|
"max": 2.6111817, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002608217842857146, |
|
"min": 0.0002608217842857146, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003651504980000004, |
|
"min": 0.003651504980000004, |
|
"max": 0.12113705182999998, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.013618141412734985, |
|
"min": 0.01267623994499445, |
|
"max": 0.3824021816253662, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.1906539797782898, |
|
"min": 0.18613320589065552, |
|
"max": 2.6768152713775635, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 630.6521739130435, |
|
"min": 630.6521739130435, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29010.0, |
|
"min": 15984.0, |
|
"max": 32779.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 0.7551377536522017, |
|
"min": -1.0000000521540642, |
|
"max": 0.7551377536522017, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 33.98119891434908, |
|
"min": -30.296201653778553, |
|
"max": 33.98119891434908, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 0.7551377536522017, |
|
"min": -1.0000000521540642, |
|
"max": 0.7551377536522017, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 33.98119891434908, |
|
"min": -30.296201653778553, |
|
"max": 33.98119891434908, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.08766814472619444, |
|
"min": 0.08766814472619444, |
|
"max": 7.7779965894296765, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.94506651267875, |
|
"min": 3.830692776129581, |
|
"max": 124.44794543087482, |
|
"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": "1674121737", |
|
"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": "1674123831" |
|
}, |
|
"total": 2093.518490296, |
|
"count": 1, |
|
"self": 0.49521606100006466, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.09976056200002859, |
|
"count": 1, |
|
"self": 0.09976056200002859 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2092.923513673, |
|
"count": 1, |
|
"self": 1.5429471820812068, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 13.736347672000193, |
|
"count": 1, |
|
"self": 13.736347672000193 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2077.5507914259188, |
|
"count": 63257, |
|
"self": 1.5786719479056046, |
|
"children": { |
|
"env_step": { |
|
"total": 1414.5920317610512, |
|
"count": 63257, |
|
"self": 1294.5667984419856, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 119.05207096897948, |
|
"count": 63257, |
|
"self": 4.683615309970264, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 114.36845565900921, |
|
"count": 62556, |
|
"self": 37.836475124995104, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 76.53198053401411, |
|
"count": 62556, |
|
"self": 76.53198053401411 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.9731623500861133, |
|
"count": 63257, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2087.7769159260133, |
|
"count": 63257, |
|
"is_parallel": true, |
|
"self": 902.135521506028, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0017834880000009434, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006232750001800014, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001160212999820942, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001160212999820942 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.044435861999772897, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004601699993145303, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00043730000015784753, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00043730000015784753 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04194584200013196, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04194584200013196 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015925500001685577, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004060200008098036, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011865299993587541, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011865299993587541 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1185.6413944199853, |
|
"count": 63256, |
|
"is_parallel": true, |
|
"self": 28.711528097953305, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.32477447205747, |
|
"count": 63256, |
|
"is_parallel": true, |
|
"self": 22.32477447205747 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1032.1452526740413, |
|
"count": 63256, |
|
"is_parallel": true, |
|
"self": 1032.1452526740413 |
|
}, |
|
"steps_from_proto": { |
|
"total": 102.45983917593321, |
|
"count": 63256, |
|
"is_parallel": true, |
|
"self": 23.302325955316064, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 79.15751322061715, |
|
"count": 506048, |
|
"is_parallel": true, |
|
"self": 79.15751322061715 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 661.380087716962, |
|
"count": 63257, |
|
"self": 2.9075301539346583, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 145.5607109790244, |
|
"count": 63257, |
|
"self": 145.33582122402368, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.22488975500073138, |
|
"count": 2, |
|
"self": 0.22488975500073138 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 512.9118465840029, |
|
"count": 452, |
|
"self": 189.4668510729648, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 323.4449955110381, |
|
"count": 22791, |
|
"self": 323.4449955110381 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.819997674436308e-07, |
|
"count": 1, |
|
"self": 8.819997674436308e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09342651099996147, |
|
"count": 1, |
|
"self": 0.0016105300001072465, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09181598099985422, |
|
"count": 1, |
|
"self": 0.09181598099985422 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |