{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6243898272514343, "min": 0.5674708485603333, "max": 1.454408049583435, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18651.7734375, "min": 17024.125, "max": 44120.921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989921.0, "min": 29952.0, "max": 989921.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989921.0, "min": 29952.0, "max": 989921.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.03518611937761307, "min": -0.17778491973876953, "max": 0.03518611937761307, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 8.585412979125977, "min": -42.13502502441406, "max": 8.585412979125977, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012558316811919212, "min": 0.01059811096638441, "max": 0.29910263419151306, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.0642292499542236, "min": 2.543546676635742, "max": 72.08373260498047, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06582622735212292, "min": 0.06286433482914706, "max": 0.07375932751090221, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9215671829297208, "min": 0.5001349717679022, "max": 1.0164294768959128, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.004203066073105653, "min": 5.0809603782794514e-05, "max": 0.010968095950336019, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.05884292502347913, "min": 0.0006605248491763287, "max": 0.07840822366900586, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.263654721671429e-06, "min": 7.263654721671429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001016911661034, "min": 0.0001016911661034, "max": 0.0033307068897644, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242118571428571, "min": 0.10242118571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338966, "min": 1.3886848, "max": 2.3169052, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002518764528571429, "min": 0.0002518764528571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035262703400000006, "min": 0.0035262703400000006, "max": 0.11103253644000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01492735743522644, "min": 0.01492735743522644, "max": 0.4478795826435089, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20898300409317017, "min": 0.20898300409317017, "max": 3.1351571083068848, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 855.2222222222222, "min": 852.2727272727273, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30788.0, "min": 15984.0, "max": 32408.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.133427820685837, "min": -1.0000000521540642, "max": -0.06475763135787213, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -4.803401544690132, "min": -31.9980016797781, "max": -2.13700183480978, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.133427820685837, "min": -1.0000000521540642, "max": -0.06475763135787213, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -4.803401544690132, "min": -31.9980016797781, "max": -2.13700183480978, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.1318850523417091, "min": 0.1318850523417091, "max": 8.805015672929585, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.747861884301528, "min": 4.558996976353228, "max": 140.88025076687336, "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": "1682325944", "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": "1682327981" }, "total": 2037.066445472, "count": 1, "self": 0.4762949059997936, "children": { "run_training.setup": { "total": 0.17502914700003203, "count": 1, "self": 0.17502914700003203 }, "TrainerController.start_learning": { "total": 2036.4151214190001, "count": 1, "self": 1.4348967679134148, "children": { "TrainerController._reset_env": { "total": 4.849771162999787, "count": 1, "self": 4.849771162999787 }, "TrainerController.advance": { "total": 2030.0306145090872, "count": 63055, "self": 1.5257392391340545, "children": { "env_step": { "total": 1427.2917346609993, "count": 63055, "self": 1317.669803294001, "children": { "SubprocessEnvManager._take_step": { "total": 108.7762585750354, "count": 63055, "self": 4.908421222097331, "children": { "TorchPolicy.evaluate": { "total": 103.86783735293807, "count": 62547, "self": 103.86783735293807 } } }, "workers": { "total": 0.8456727919628975, "count": 63055, "self": 0.0, "children": { "worker_root": { "total": 2031.5331836010184, "count": 63055, "is_parallel": true, "self": 825.7903345240452, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024519900000541384, "count": 1, "is_parallel": true, "self": 0.0007024989997717057, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017494910002824327, "count": 8, "is_parallel": true, "self": 0.0017494910002824327 } } }, "UnityEnvironment.step": { "total": 0.04602847199998905, "count": 1, "is_parallel": true, "self": 0.0005377929999212938, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005566740001086146, "count": 1, "is_parallel": true, "self": 0.0005566740001086146 }, "communicator.exchange": { "total": 0.04337915199994313, "count": 1, "is_parallel": true, "self": 0.04337915199994313 }, "steps_from_proto": { "total": 0.00155485300001601, "count": 1, "is_parallel": true, "self": 0.00034332399991399143, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012115290001020185, "count": 8, "is_parallel": true, "self": 0.0012115290001020185 } } } } } } }, "UnityEnvironment.step": { "total": 1205.7428490769732, "count": 63054, "is_parallel": true, "self": 32.44478067513455, "children": { "UnityEnvironment._generate_step_input": { "total": 24.375522333941944, "count": 63054, "is_parallel": true, "self": 24.375522333941944 }, "communicator.exchange": { "total": 1051.5703677829727, "count": 63054, "is_parallel": true, "self": 1051.5703677829727 }, "steps_from_proto": { "total": 97.3521782849241, "count": 63054, "is_parallel": true, "self": 20.93598629879375, "children": { "_process_rank_one_or_two_observation": { "total": 76.41619198613034, "count": 504432, "is_parallel": true, "self": 76.41619198613034 } } } } } } } } } } }, "trainer_advance": { "total": 601.2131406089538, "count": 63055, "self": 2.2874602629233323, "children": { "process_trajectory": { "total": 105.3291275310196, "count": 63055, "self": 105.1213864900194, "children": { "RLTrainer._checkpoint": { "total": 0.2077410410001903, "count": 2, "self": 0.2077410410001903 } } }, "_update_policy": { "total": 493.5965528150109, "count": 432, "self": 312.4039116979902, "children": { "TorchPPOOptimizer.update": { "total": 181.19264111702068, "count": 22863, "self": 181.19264111702068 } } } } } } }, "trainer_threads": { "total": 9.109999155043624e-07, "count": 1, "self": 9.109999155043624e-07 }, "TrainerController._save_models": { "total": 0.09983806799982631, "count": 1, "self": 0.0013638139994327503, "children": { "RLTrainer._checkpoint": { "total": 0.09847425400039356, "count": 1, "self": 0.09847425400039356 } } } } } } }