{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2844931185245514, "min": 0.24472716450691223, "max": 1.3701759576797485, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8484.72265625, "min": 7326.15234375, "max": 41565.65625, "count": 33 }, "Pyramids.Step.mean": { "value": 989947.0, "min": 29952.0, "max": 989947.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989947.0, "min": 29952.0, "max": 989947.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4983386695384979, "min": -0.05905454233288765, "max": 0.5645862817764282, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 133.05642700195312, "min": -14.173089981079102, "max": 156.95498657226562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07930433750152588, "min": 0.04820664972066879, "max": 0.5920436978340149, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 21.174257278442383, "min": 13.401448249816895, "max": 140.31436157226562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06924574435334745, "min": 0.06575790516771597, "max": 0.07436230087004529, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9694404209468642, "min": 0.5041763421195564, "max": 1.1154345130506793, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016617537143792504, "min": 0.00041742201084485906, "max": 0.023507672734489286, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23264552001309508, "min": 0.005009064130138309, "max": 0.24892463072319515, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3663404017285724e-06, "min": 7.3663404017285724e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010312876562420002, "min": 0.00010312876562420002, "max": 0.0033831311722897005, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024554142857143, "min": 0.1024554142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343758000000002, "min": 1.3886848, "max": 2.5277103000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025529588714285717, "min": 0.00025529588714285717, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035741424200000007, "min": 0.0035741424200000007, "max": 0.11279825897000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.09361807256937027, "min": 0.09361807256937027, "max": 0.6412447094917297, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.3106529712677002, "min": 1.3106529712677002, "max": 4.488712787628174, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 376.4810126582278, "min": 319.0421052631579, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29742.0, "min": 15984.0, "max": 32676.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.547554408447652, "min": -1.0000000521540642, "max": 1.629106791097332, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 122.2567982673645, "min": -30.997601620852947, "max": 149.6873982846737, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.547554408447652, "min": -1.0000000521540642, "max": 1.629106791097332, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 122.2567982673645, "min": -30.997601620852947, "max": 149.6873982846737, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.36060919682347936, "min": 0.3063813652417402, "max": 14.314660960808396, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 28.48812654905487, "min": 28.48812654905487, "max": 229.03457537293434, "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": "1714297736", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714300511" }, "total": 2774.483292715, "count": 1, "self": 0.21989113700055896, "children": { "run_training.setup": { "total": 0.029097946999172564, "count": 1, "self": 0.029097946999172564 }, "TrainerController.start_learning": { "total": 2774.2343036310003, "count": 1, "self": 1.0496080911252648, "children": { "TrainerController._reset_env": { "total": 2.9551966649996757, "count": 1, "self": 2.9551966649996757 }, "TrainerController.advance": { "total": 2770.1440743158746, "count": 63816, "self": 1.0557393588942432, "children": { "env_step": { "total": 1309.7799356699252, "count": 63816, "self": 849.6533611398509, "children": { "SubprocessEnvManager._take_step": { "total": 459.4117601110347, "count": 63816, "self": 3.401074708127453, "children": { "TorchPolicy.evaluate": { "total": 456.01068540290726, "count": 62556, "self": 456.01068540290726 } } }, "workers": { "total": 0.7148144190396124, "count": 63816, "self": 0.0, "children": { "worker_root": { "total": 2771.616885570029, "count": 63816, "is_parallel": true, "self": 1998.0035955469875, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001137096999627829, "count": 1, "is_parallel": true, "self": 0.0003546030011420953, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007824939984857338, "count": 8, "is_parallel": true, "self": 0.0007824939984857338 } } }, "UnityEnvironment.step": { "total": 0.024306231999617012, "count": 1, "is_parallel": true, "self": 0.0002414619993942324, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001651660004426958, "count": 1, "is_parallel": true, "self": 0.0001651660004426958 }, "communicator.exchange": { "total": 0.02337368099961168, "count": 1, "is_parallel": true, "self": 0.02337368099961168 }, "steps_from_proto": { "total": 0.0005259230001684045, "count": 1, "is_parallel": true, "self": 0.00013071399916952942, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003952090009988751, "count": 8, "is_parallel": true, "self": 0.0003952090009988751 } } } } } } }, "UnityEnvironment.step": { "total": 773.6132900230414, "count": 63815, "is_parallel": true, "self": 14.024843097138728, "children": { "UnityEnvironment._generate_step_input": { "total": 8.593827352072367, "count": 63815, "is_parallel": true, "self": 8.593827352072367 }, "communicator.exchange": { "total": 715.6214158859184, "count": 63815, "is_parallel": true, "self": 715.6214158859184 }, "steps_from_proto": { "total": 35.37320368791188, "count": 63815, "is_parallel": true, "self": 8.85180411994952, "children": { "_process_rank_one_or_two_observation": { "total": 26.521399567962362, "count": 510520, "is_parallel": true, "self": 26.521399567962362 } } } } } } } } } } }, "trainer_advance": { "total": 1459.3083992870552, "count": 63816, "self": 2.100977072036585, "children": { "process_trajectory": { "total": 194.25542743501774, "count": 63816, "self": 194.0483036280184, "children": { "RLTrainer._checkpoint": { "total": 0.2071238069993342, "count": 2, "self": 0.2071238069993342 } } }, "_update_policy": { "total": 1262.9519947800009, "count": 450, "self": 403.4750388819566, "children": { "TorchPPOOptimizer.update": { "total": 859.4769558980443, "count": 22794, "self": 859.4769558980443 } } } } } } }, "trainer_threads": { "total": 5.97000507696066e-07, "count": 1, "self": 5.97000507696066e-07 }, "TrainerController._save_models": { "total": 0.08542396200027724, "count": 1, "self": 0.0006400240008588298, "children": { "RLTrainer._checkpoint": { "total": 0.08478393799941841, "count": 1, "self": 0.08478393799941841 } } } } } } }