{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8653649687767029, "min": 0.696636438369751, "max": 1.4100573062896729, "count": 21 }, "Pyramids.Policy.Entropy.sum": { "value": 26237.865234375, "min": 21066.28515625, "max": 42775.5, "count": 21 }, "Pyramids.Step.mean": { "value": 629950.0, "min": 29952.0, "max": 629950.0, "count": 21 }, "Pyramids.Step.sum": { "value": 629950.0, "min": 29952.0, "max": 629950.0, "count": 21 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07417815923690796, "min": -0.16257144510746002, "max": -0.03592294454574585, "count": 21 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -17.951114654541016, "min": -38.52943420410156, "max": -8.729275703430176, "count": 21 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014958946965634823, "min": 0.013271074742078781, "max": 0.19380821287631989, "count": 21 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.620065212249756, "min": 3.1850578784942627, "max": 46.901588439941406, "count": 21 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06910294711418451, "min": 0.06478099469286235, "max": 0.07426592190670049, "count": 21 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9674412595985832, "min": 0.5035416520170228, "max": 1.0538863375453125, "count": 21 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0007485693214026528, "min": 6.67143164093629e-05, "max": 0.00487186843172953, "count": 21 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.010479970499637139, "min": 0.0008672861133217178, "max": 0.05996229362685256, "count": 21 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00023851489906646903, "min": 0.00023851489906646903, "max": 0.00029838354339596195, "count": 21 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0033392085869305664, "min": 0.0020886848037717336, "max": 0.0038024436325188, "count": 21 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.17950495952380954, "min": 0.17950495952380954, "max": 0.19946118095238097, "count": 21 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.5130694333333334, "min": 1.3962282666666668, "max": 2.7674636333333336, "count": 21 }, "Pyramids.Policy.Beta.mean": { "value": 0.007952545456428572, "min": 0.007952545456428572, "max": 0.009946171977142856, "count": 21 }, "Pyramids.Policy.Beta.sum": { "value": 0.11133563639, "min": 0.06962320384, "max": 0.12676961697, "count": 21 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01625954546034336, "min": 0.01625954546034336, "max": 0.36111146211624146, "count": 21 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22763362526893616, "min": 0.22763362526893616, "max": 2.527780294418335, "count": 21 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 966.5, "min": 882.9705882352941, "max": 999.0, "count": 21 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30928.0, "min": 15984.0, "max": 33019.0, "count": 21 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.779668798437342, "min": -1.0000000521540642, "max": -0.41301769346875306, "count": 21 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -24.949401549994946, "min": -31.998001664876938, "max": -14.042601577937603, "count": 21 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.779668798437342, "min": -1.0000000521540642, "max": -0.41301769346875306, "count": 21 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -24.949401549994946, "min": -31.998001664876938, "max": -14.042601577937603, "count": 21 }, "Pyramids.Policy.RndReward.mean": { "value": 0.16407702981086913, "min": 0.16407702981086913, "max": 6.558580571785569, "count": 21 }, "Pyramids.Policy.RndReward.sum": { "value": 5.250464953947812, "min": 5.250464953947812, "max": 104.9372891485691, "count": 21 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 21 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 21 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1703520289", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703521566" }, "total": 1276.3284580929999, "count": 1, "self": 0.493175557000086, "children": { "run_training.setup": { "total": 0.05417933700005051, "count": 1, "self": 0.05417933700005051 }, "TrainerController.start_learning": { "total": 1275.7811031989997, "count": 1, "self": 0.8139817919957295, "children": { "TrainerController._reset_env": { "total": 2.0362777450000067, "count": 1, "self": 2.0362777450000067 }, "TrainerController.advance": { "total": 1272.9272560610038, "count": 39808, "self": 0.853851328017754, "children": { "env_step": { "total": 881.918124496023, "count": 39808, "self": 803.3392179180603, "children": { "SubprocessEnvManager._take_step": { "total": 78.088698361036, "count": 39808, "self": 2.8598763800455345, "children": { "TorchPolicy.evaluate": { "total": 75.22882198099046, "count": 39612, "self": 75.22882198099046 } } }, "workers": { "total": 0.49020821692670324, "count": 39808, "self": 0.0, "children": { "worker_root": { "total": 1272.8924486930418, "count": 39808, "is_parallel": true, "self": 540.2442838990144, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018245910000587173, "count": 1, "is_parallel": true, "self": 0.0005732650004119932, "children": { "_process_rank_one_or_two_observation": { "total": 0.001251325999646724, "count": 8, "is_parallel": true, "self": 0.001251325999646724 } } }, "UnityEnvironment.step": { "total": 0.05229469000005338, "count": 1, "is_parallel": true, "self": 0.0005633579999084759, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005113400000027468, "count": 1, "is_parallel": true, "self": 0.0005113400000027468 }, "communicator.exchange": { "total": 0.049173658000199794, "count": 1, "is_parallel": true, "self": 0.049173658000199794 }, "steps_from_proto": { "total": 0.0020463339999423624, "count": 1, "is_parallel": true, "self": 0.00043597400008366094, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016103599998587015, "count": 8, "is_parallel": true, "self": 0.0016103599998587015 } } } } } } }, "UnityEnvironment.step": { "total": 732.6481647940275, "count": 39807, "is_parallel": true, "self": 21.375438582042307, "children": { "UnityEnvironment._generate_step_input": { "total": 15.145237243002157, "count": 39807, "is_parallel": true, "self": 15.145237243002157 }, "communicator.exchange": { "total": 635.597081579934, "count": 39807, "is_parallel": true, "self": 635.597081579934 }, "steps_from_proto": { "total": 60.53040738904906, "count": 39807, "is_parallel": true, "self": 11.691484828160128, "children": { "_process_rank_one_or_two_observation": { "total": 48.83892256088893, "count": 318456, "is_parallel": true, "self": 48.83892256088893 } } } } } } } } } } }, "trainer_advance": { "total": 390.1552802369631, "count": 39808, "self": 1.434370235954475, "children": { "process_trajectory": { "total": 75.93375816700541, "count": 39808, "self": 75.8342619370053, "children": { "RLTrainer._checkpoint": { "total": 0.09949623000011343, "count": 1, "self": 0.09949623000011343 } } }, "_update_policy": { "total": 312.7871518340032, "count": 273, "self": 187.06933069801062, "children": { "TorchPPOOptimizer.update": { "total": 125.71782113599261, "count": 14397, "self": 125.71782113599261 } } } } } } }, "trainer_threads": { "total": 1.2840000636060722e-06, "count": 1, "self": 1.2840000636060722e-06 }, "TrainerController._save_models": { "total": 0.0035863170000993705, "count": 1, "self": 3.375799997229478e-05, "children": { "RLTrainer._checkpoint": { "total": 0.0035525590001270757, "count": 1, "self": 0.0035525590001270757 } } } } } } }