{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8432455062866211, "min": 0.7748345732688904, "max": 1.4863959550857544, "count": 6 }, "Pyramids.Policy.Entropy.sum": { "value": 25513.236328125, "min": 23269.83203125, "max": 45091.30859375, "count": 6 }, "Pyramids.Step.mean": { "value": 179904.0, "min": 29952.0, "max": 179904.0, "count": 6 }, "Pyramids.Step.sum": { "value": 179904.0, "min": 29952.0, "max": 179904.0, "count": 6 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.08838693797588348, "min": -0.08838693797588348, "max": -0.008708351291716099, "count": 6 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -21.212865829467773, "min": -21.212865829467773, "max": -2.0638792514801025, "count": 6 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06572914123535156, "min": 0.06572914123535156, "max": 0.40303322672843933, "count": 6 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 15.774993896484375, "min": 15.774993896484375, "max": 95.51887512207031, "count": 6 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06883439517709176, "min": 0.06859577133558689, "max": 0.07118776443726743, "count": 6 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8948471373021929, "min": 0.498314351060872, "max": 0.9755370049420486, "count": 6 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.001465718373879852, "min": 0.0005050577106264193, "max": 0.008113788669759352, "count": 6 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.019054338860438075, "min": 0.006565750238143451, "max": 0.05679652068831546, "count": 6 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.267846705592307e-05, "min": 5.267846705592307e-05, "max": 0.00027575315093942855, "count": 6 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0006848200717269999, "min": 0.0006848200717269999, "max": 0.0022379914540029996, "count": 6 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.11755946153846154, "min": 0.11755946153846154, "max": 0.19191771428571427, "count": 6 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.528273, "min": 1.343424, "max": 2.0645485000000003, "count": 6 }, "Pyramids.Policy.Beta.mean": { "value": 0.0017641902076923081, "min": 0.0017641902076923081, "max": 0.009192579657142857, "count": 6 }, "Pyramids.Policy.Beta.sum": { "value": 0.022934472700000007, "min": 0.022934472700000007, "max": 0.07464510029999999, "count": 6 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.05767832323908806, "min": 0.05767832323908806, "max": 0.4827132821083069, "count": 6 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.7498182058334351, "min": 0.7498182058334351, "max": 3.378993034362793, "count": 6 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 998.5666666666667, "min": 935.2857142857143, "max": 999.0, "count": 6 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29957.0, "min": 15984.0, "max": 32735.0, "count": 6 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8703355337342908, "min": -1.0000000521540642, "max": -0.593194339956556, "count": 6 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -26.980401545763016, "min": -29.79600165039301, "max": -16.000000834465027, "count": 6 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8703355337342908, "min": -1.0000000521540642, "max": -0.593194339956556, "count": 6 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -26.980401545763016, "min": -29.79600165039301, "max": -16.000000834465027, "count": 6 }, "Pyramids.Policy.RndReward.mean": { "value": 0.5926603963298183, "min": 0.5926603963298183, "max": 10.024078987538815, "count": 6 }, "Pyramids.Policy.RndReward.sum": { "value": 18.372472286224365, "min": 18.372472286224365, "max": 160.38526380062103, "count": 6 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1775901118", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1775901577" }, "total": 459.4837723989999, "count": 1, "self": 0.48144437699966147, "children": { "run_training.setup": { "total": 0.022453537000274082, "count": 1, "self": 0.022453537000274082 }, "TrainerController.start_learning": { "total": 458.979874485, "count": 1, "self": 0.34253719701155205, "children": { "TrainerController._reset_env": { "total": 2.3143615670001054, "count": 1, "self": 2.3143615670001054 }, "TrainerController.advance": { "total": 456.20926580898777, "count": 12603, "self": 0.33338913894840516, "children": { "env_step": { "total": 317.0827324360289, "count": 12603, "self": 280.3740466449958, "children": { "SubprocessEnvManager._take_step": { "total": 36.50708990202838, "count": 12603, "self": 1.0589017090055677, "children": { "TorchPolicy.evaluate": { "total": 35.448188193022816, "count": 12551, "self": 35.448188193022816 } } }, "workers": { "total": 0.20159588900469316, "count": 12603, "self": 0.0, "children": { "worker_root": { "total": 457.54095455197466, "count": 12603, "is_parallel": true, "self": 204.15030256198634, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028410749996510276, "count": 1, "is_parallel": true, "self": 0.0007043899991003855, "children": { "_process_rank_one_or_two_observation": { "total": 0.002136685000550642, "count": 8, "is_parallel": true, "self": 0.002136685000550642 } } }, "UnityEnvironment.step": { "total": 0.05452450300026612, "count": 1, "is_parallel": true, "self": 0.0005860710002707492, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004668719998335291, "count": 1, "is_parallel": true, "self": 0.0004668719998335291 }, "communicator.exchange": { "total": 0.05167644399989513, "count": 1, "is_parallel": true, "self": 0.05167644399989513 }, "steps_from_proto": { "total": 0.0017951160002667166, "count": 1, "is_parallel": true, "self": 0.0003673590008475003, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014277569994192163, "count": 8, "is_parallel": true, "self": 0.0014277569994192163 } } } } } } }, "UnityEnvironment.step": { "total": 253.39065198998833, "count": 12602, "is_parallel": true, "self": 7.499947982949379, "children": { "UnityEnvironment._generate_step_input": { "total": 5.150102415992933, "count": 12602, "is_parallel": true, "self": 5.150102415992933 }, "communicator.exchange": { "total": 215.86857656501934, "count": 12602, "is_parallel": true, "self": 215.86857656501934 }, "steps_from_proto": { "total": 24.872025026026677, "count": 12602, "is_parallel": true, "self": 5.28351131999716, "children": { "_process_rank_one_or_two_observation": { "total": 19.588513706029516, "count": 100816, "is_parallel": true, "self": 19.588513706029516 } } } } } } } } } } }, "trainer_advance": { "total": 138.79314423401047, "count": 12603, "self": 0.5477806980270543, "children": { "process_trajectory": { "total": 25.695744830981766, "count": 12603, "self": 25.695744830981766 }, "_update_policy": { "total": 112.54961870500165, "count": 77, "self": 61.925967989993296, "children": { "TorchPPOOptimizer.update": { "total": 50.62365071500835, "count": 4557, "self": 50.62365071500835 } } } } } } }, "trainer_threads": { "total": 1.0450003173900768e-06, "count": 1, "self": 1.0450003173900768e-06 }, "TrainerController._save_models": { "total": 0.1137088670002413, "count": 1, "self": 0.0009950070002560096, "children": { "RLTrainer._checkpoint": { "total": 0.11271385999998529, "count": 1, "self": 0.11271385999998529 } } } } } } }