{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4802834391593933, "min": 0.4394834339618683, "max": 1.496106505393982, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14416.1875, "min": 13086.05859375, "max": 45385.88671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.19349706172943115, "min": -0.12085083872079849, "max": 0.2165093719959259, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 49.14825439453125, "min": -29.125051498413086, "max": 55.70112991333008, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016944028437137604, "min": 0.012779024429619312, "max": 0.34925752878189087, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.303783416748047, "min": 3.2969882488250732, "max": 83.82180786132812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06860056467121467, "min": 0.06518728253174005, "max": 0.07311340238217896, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9604079053970054, "min": 0.5011475350016638, "max": 1.0456642894971404, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011602725109696621, "min": 0.00016168859184817057, "max": 0.013789984603507915, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1624381515357527, "min": 0.002263640285874388, "max": 0.20017785062251883, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.226583305457138e-06, "min": 7.226583305457138e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010117216627639993, "min": 0.00010117216627639993, "max": 0.003258096313968, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10240882857142859, "min": 0.10240882857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4337236000000002, "min": 1.3691136000000002, "max": 2.486032, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025064197428571413, "min": 0.00025064197428571413, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003508987639999998, "min": 0.003508987639999998, "max": 0.1086345968, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009710184298455715, "min": 0.009710184298455715, "max": 0.5651816725730896, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13594257831573486, "min": 0.13594257831573486, "max": 3.9562718868255615, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 640.063829787234, "min": 566.8076923076923, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30083.0, "min": 15984.0, "max": 32621.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8491106025399046, "min": -1.0000000521540642, "max": 1.0472041342097025, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 39.908198319375515, "min": -32.000001668930054, "max": 50.51959864795208, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8491106025399046, "min": -1.0000000521540642, "max": 1.0472041342097025, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 39.908198319375515, "min": -32.000001668930054, "max": 50.51959864795208, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06592986668754824, "min": 0.06592986668754824, "max": 12.113419394940138, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0987037343147676, "min": 3.0987037343147676, "max": 193.8147103190422, "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": "1679841717", "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 /content/ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "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": "1679843651" }, "total": 1934.3137400629998, "count": 1, "self": 0.4401219310002489, "children": { "run_training.setup": { "total": 0.1080484629997045, "count": 1, "self": 0.1080484629997045 }, "TrainerController.start_learning": { "total": 1933.765569669, "count": 1, "self": 1.247233284889262, "children": { "TrainerController._reset_env": { "total": 6.010659531999863, "count": 1, "self": 6.010659531999863 }, "TrainerController.advance": { "total": 1926.4152962431103, "count": 63411, "self": 1.3019417050768425, "children": { "env_step": { "total": 1314.1835992629358, "count": 63411, "self": 1211.8214800967917, "children": { "SubprocessEnvManager._take_step": { "total": 101.61660811602906, "count": 63411, "self": 4.45069326494513, "children": { "TorchPolicy.evaluate": { "total": 97.16591485108393, "count": 62565, "self": 97.16591485108393 } } }, "workers": { "total": 0.7455110501150557, "count": 63411, "self": 0.0, "children": { "worker_root": { "total": 1929.8647541949736, "count": 63411, "is_parallel": true, "self": 826.5711878789598, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019421179999881133, "count": 1, "is_parallel": true, "self": 0.0005405749993769859, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014015430006111274, "count": 8, "is_parallel": true, "self": 0.0014015430006111274 } } }, "UnityEnvironment.step": { "total": 0.04410140300024068, "count": 1, "is_parallel": true, "self": 0.000516343000526831, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004481040000428038, "count": 1, "is_parallel": true, "self": 0.0004481040000428038 }, "communicator.exchange": { "total": 0.04162853899970287, "count": 1, "is_parallel": true, "self": 0.04162853899970287 }, "steps_from_proto": { "total": 0.0015084169999681762, "count": 1, "is_parallel": true, "self": 0.00033355499954268453, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011748620004254917, "count": 8, "is_parallel": true, "self": 0.0011748620004254917 } } } } } } }, "UnityEnvironment.step": { "total": 1103.2935663160138, "count": 63410, "is_parallel": true, "self": 30.079761177844375, "children": { "UnityEnvironment._generate_step_input": { "total": 22.055548687953888, "count": 63410, "is_parallel": true, "self": 22.055548687953888 }, "communicator.exchange": { "total": 963.2545508810708, "count": 63410, "is_parallel": true, "self": 963.2545508810708 }, "steps_from_proto": { "total": 87.90370556914468, "count": 63410, "is_parallel": true, "self": 18.113497855954392, "children": { "_process_rank_one_or_two_observation": { "total": 69.79020771319028, "count": 507280, "is_parallel": true, "self": 69.79020771319028 } } } } } } } } } } }, "trainer_advance": { "total": 610.9297552750977, "count": 63411, "self": 2.3649194962526963, "children": { "process_trajectory": { "total": 110.98369888784964, "count": 63411, "self": 110.77676136784976, "children": { "RLTrainer._checkpoint": { "total": 0.20693751999988308, "count": 2, "self": 0.20693751999988308 } } }, "_update_policy": { "total": 497.58113689099537, "count": 444, "self": 317.5126000310256, "children": { "TorchPPOOptimizer.update": { "total": 180.06853685996975, "count": 22767, "self": 180.06853685996975 } } } } } } }, "trainer_threads": { "total": 8.520000847056508e-07, "count": 1, "self": 8.520000847056508e-07 }, "TrainerController._save_models": { "total": 0.0923797570003444, "count": 1, "self": 0.001430756000445399, "children": { "RLTrainer._checkpoint": { "total": 0.090949000999899, "count": 1, "self": 0.090949000999899 } } } } } } }