{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4543881118297577, "min": 0.4543881118297577, "max": 1.4955379962921143, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13689.8046875, "min": 13689.8046875, "max": 45368.640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989953.0, "min": 29952.0, "max": 989953.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989953.0, "min": 29952.0, "max": 989953.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.33823418617248535, "min": -0.09899292141199112, "max": 0.3448600769042969, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 88.61735534667969, "min": -23.75830078125, "max": 90.00847625732422, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.005373472347855568, "min": -0.02219024859368801, "max": 0.4490368068218231, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.4078497886657715, "min": -5.7028937339782715, "max": 106.42172241210938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06741406548858826, "min": 0.0650688330926854, "max": 0.07364380269028319, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.011210982328824, "min": 0.47501679374896605, "max": 1.1046570403542477, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012859277964808926, "min": 0.00025897036434979, "max": 0.01429357355486938, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1928891694721339, "min": 0.0033666147365472698, "max": 0.20011002976817133, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.437557520846668e-06, "min": 7.437557520846668e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011156336281270001, "min": 0.00011156336281270001, "max": 0.0035084381305206997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247915333333332, "min": 0.10247915333333332, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5371872999999998, "min": 1.3691136000000002, "max": 2.5694793000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025766741800000006, "min": 0.00025766741800000006, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038650112700000013, "min": 0.0038650112700000013, "max": 0.11697098207, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006562925409525633, "min": 0.006562925409525633, "max": 0.3571026027202606, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0984438806772232, "min": 0.09620210528373718, "max": 2.499718189239502, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 501.4193548387097, "min": 491.3220338983051, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31088.0, "min": 15984.0, "max": 33098.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2726935190298865, "min": -1.0000000521540642, "max": 1.3322881160903786, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 78.90699817985296, "min": -32.000001668930054, "max": 78.90699817985296, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2726935190298865, "min": -1.0000000521540642, "max": 1.3322881160903786, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 78.90699817985296, "min": -32.000001668930054, "max": 78.90699817985296, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.034094517155843336, "min": 0.034094517155843336, "max": 7.5563646517694, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.113860063662287, "min": 2.113860063662287, "max": 120.9018344283104, "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": "1686827073", "python_version": "3.10.8 | packaged by conda-forge | (main, Nov 22 2022, 08:23:14) [GCC 10.4.0]", "command_line_arguments": "/home/ditrip/anaconda3/envs/my-env/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": "1686828461" }, "total": 1387.968498837, "count": 1, "self": 0.32015722000005553, "children": { "run_training.setup": { "total": 0.01289636999990762, "count": 1, "self": 0.01289636999990762 }, "TrainerController.start_learning": { "total": 1387.635445247, "count": 1, "self": 1.2468891640187394, "children": { "TrainerController._reset_env": { "total": 3.0110228290000123, "count": 1, "self": 3.0110228290000123 }, "TrainerController.advance": { "total": 1383.298689181982, "count": 63512, "self": 1.196264015106408, "children": { "env_step": { "total": 886.0539490079168, "count": 63512, "self": 787.773319458945, "children": { "SubprocessEnvManager._take_step": { "total": 97.47178604596502, "count": 63512, "self": 3.7320215489644397, "children": { "TorchPolicy.evaluate": { "total": 93.73976449700058, "count": 62568, "self": 93.73976449700058 } } }, "workers": { "total": 0.8088435030067558, "count": 63512, "self": 0.0, "children": { "worker_root": { "total": 1385.95326658794, "count": 63512, "is_parallel": true, "self": 685.7705926149042, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010758079997685854, "count": 1, "is_parallel": true, "self": 0.0003052649990422651, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007705430007263203, "count": 8, "is_parallel": true, "self": 0.0007705430007263203 } } }, "UnityEnvironment.step": { "total": 0.024916614999710873, "count": 1, "is_parallel": true, "self": 0.00024742100004004897, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001962069995897764, "count": 1, "is_parallel": true, "self": 0.0001962069995897764 }, "communicator.exchange": { "total": 0.023688052000125026, "count": 1, "is_parallel": true, "self": 0.023688052000125026 }, "steps_from_proto": { "total": 0.0007849349999560218, "count": 1, "is_parallel": true, "self": 0.00017840399959823117, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006065310003577906, "count": 8, "is_parallel": true, "self": 0.0006065310003577906 } } } } } } }, "UnityEnvironment.step": { "total": 700.1826739730359, "count": 63511, "is_parallel": true, "self": 23.768720990076872, "children": { "UnityEnvironment._generate_step_input": { "total": 14.897164641992276, "count": 63511, "is_parallel": true, "self": 14.897164641992276 }, "communicator.exchange": { "total": 593.8965361779633, "count": 63511, "is_parallel": true, "self": 593.8965361779633 }, "steps_from_proto": { "total": 67.62025216300344, "count": 63511, "is_parallel": true, "self": 14.158390328091173, "children": { "_process_rank_one_or_two_observation": { "total": 53.46186183491227, "count": 508088, "is_parallel": true, "self": 53.46186183491227 } } } } } } } } } } }, "trainer_advance": { "total": 496.0484761589587, "count": 63512, "self": 1.9796729159029383, "children": { "process_trajectory": { "total": 83.96095536806115, "count": 63512, "self": 83.77526621706102, "children": { "RLTrainer._checkpoint": { "total": 0.18568915100013328, "count": 2, "self": 0.18568915100013328 } } }, "_update_policy": { "total": 410.1078478749946, "count": 446, "self": 272.98434980703223, "children": { "TorchPPOOptimizer.update": { "total": 137.12349806796237, "count": 22782, "self": 137.12349806796237 } } } } } } }, "trainer_threads": { "total": 8.999995770864189e-07, "count": 1, "self": 8.999995770864189e-07 }, "TrainerController._save_models": { "total": 0.07884317199977886, "count": 1, "self": 0.0010180279996347963, "children": { "RLTrainer._checkpoint": { "total": 0.07782514400014406, "count": 1, "self": 0.07782514400014406 } } } } } } }