{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38564544916152954, "min": 0.27187255024909973, "max": 1.5031646490097046, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11520.0009765625, "min": 8143.126953125, "max": 45600.00390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989913.0, "min": 29952.0, "max": 989913.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989913.0, "min": 29952.0, "max": 989913.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1571851372718811, "min": -0.09539750963449478, "max": 0.16879968345165253, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 39.610652923583984, "min": -22.990798950195312, "max": 42.36872100830078, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00947884377092123, "min": 0.00947884377092123, "max": 0.23489780724048615, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.3886685371398926, "min": 2.3886685371398926, "max": 56.37547302246094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06642737323939193, "min": 0.06642737323939193, "max": 0.07907054559643789, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9299832253514871, "min": 0.4980794015081584, "max": 1.056658653308884, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007760949017887957, "min": 8.361589949722398e-05, "max": 0.008563479950215539, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1086532862504314, "min": 0.0005853112964805679, "max": 0.1284521992532331, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.4361383278157136e-05, "min": 2.4361383278157136e-05, "max": 0.0009838354301878857, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0003410593658941999, "min": 0.0003410593658941999, "max": 0.009681244331875598, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243612857142857, "min": 0.10243612857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341058, "min": 1.3271040000000003, "max": 2.3590986000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 3.411767285714286e-05, "min": 3.411767285714286e-05, "max": 0.0009839970742857144, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00047764742, "min": 0.00047764742, "max": 0.00971443156, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00956515409052372, "min": 0.00956515409052372, "max": 0.3370968699455261, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13391216099262238, "min": 0.13391216099262238, "max": 2.359678030014038, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 667.0869565217391, "min": 626.3653846153846, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30686.0, "min": 15984.0, "max": 33092.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.46306518821612647, "min": -1.0000000521540642, "max": 0.6926278707592987, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 21.30099865794182, "min": -32.000001668930054, "max": 33.41519816964865, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.46306518821612647, "min": -1.0000000521540642, "max": 0.6926278707592987, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 21.30099865794182, "min": -32.000001668930054, "max": 33.41519816964865, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07198707936787167, "min": 0.07198707936787167, "max": 7.666629082988948, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3114056509220973, "min": 3.3114056509220973, "max": 122.66606532782316, "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": "1679273641", "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 --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": "1679275898" }, "total": 2257.5557592080004, "count": 1, "self": 0.5337390979984775, "children": { "run_training.setup": { "total": 0.11081395699875429, "count": 1, "self": 0.11081395699875429 }, "TrainerController.start_learning": { "total": 2256.911206153003, "count": 1, "self": 1.4002376198695856, "children": { "TrainerController._reset_env": { "total": 5.840849281001283, "count": 1, "self": 5.840849281001283 }, "TrainerController.advance": { "total": 2249.5775792731292, "count": 63194, "self": 1.4163245001145697, "children": { "env_step": { "total": 1272.4486386301141, "count": 63194, "self": 1160.49444786835, "children": { "SubprocessEnvManager._take_step": { "total": 111.10674973935602, "count": 63194, "self": 4.776577332759189, "children": { "TorchPolicy.evaluate": { "total": 106.33017240659683, "count": 62560, "self": 106.33017240659683 } } }, "workers": { "total": 0.8474410224080202, "count": 63194, "self": 0.0, "children": { "worker_root": { "total": 2252.7148664984234, "count": 63194, "is_parallel": true, "self": 1205.1513631624912, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019403209989832249, "count": 1, "is_parallel": true, "self": 0.0006599309963348787, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012803900026483461, "count": 8, "is_parallel": true, "self": 0.0012803900026483461 } } }, "UnityEnvironment.step": { "total": 0.047291327002312755, "count": 1, "is_parallel": true, "self": 0.0005638700022245757, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043040899981861003, "count": 1, "is_parallel": true, "self": 0.00043040899981861003 }, "communicator.exchange": { "total": 0.044643010001891525, "count": 1, "is_parallel": true, "self": 0.044643010001891525 }, "steps_from_proto": { "total": 0.001654037998378044, "count": 1, "is_parallel": true, "self": 0.00037594499735860154, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012780930010194425, "count": 8, "is_parallel": true, "self": 0.0012780930010194425 } } } } } } }, "UnityEnvironment.step": { "total": 1047.5635033359322, "count": 63193, "is_parallel": true, "self": 30.986389484693063, "children": { "UnityEnvironment._generate_step_input": { "total": 22.86743579751419, "count": 63193, "is_parallel": true, "self": 22.86743579751419 }, "communicator.exchange": { "total": 902.3412987935262, "count": 63193, "is_parallel": true, "self": 902.3412987935262 }, "steps_from_proto": { "total": 91.36837926019871, "count": 63193, "is_parallel": true, "self": 19.27413905605863, "children": { "_process_rank_one_or_two_observation": { "total": 72.09424020414008, "count": 505544, "is_parallel": true, "self": 72.09424020414008 } } } } } } } } } } }, "trainer_advance": { "total": 975.7126161429005, "count": 63194, "self": 2.467557238484005, "children": { "process_trajectory": { "total": 118.7491632004967, "count": 63194, "self": 118.53083047349719, "children": { "RLTrainer._checkpoint": { "total": 0.21833272699950612, "count": 2, "self": 0.21833272699950612 } } }, "_update_policy": { "total": 854.4958957039198, "count": 430, "self": 542.7714099712903, "children": { "TorchPPOOptimizer.update": { "total": 311.72448573262955, "count": 38125, "self": 311.72448573262955 } } } } } } }, "trainer_threads": { "total": 1.1660013115033507e-06, "count": 1, "self": 1.1660013115033507e-06 }, "TrainerController._save_models": { "total": 0.09253881300173816, "count": 1, "self": 0.001796526001271559, "children": { "RLTrainer._checkpoint": { "total": 0.0907422870004666, "count": 1, "self": 0.0907422870004666 } } } } } } }