{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9384244680404663, "min": 0.9384244680404663, "max": 1.4979941844940186, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 28107.689453125, "min": 28107.689453125, "max": 45443.15234375, "count": 3 }, "Pyramids.Step.mean": { "value": 89932.0, "min": 29952.0, "max": 89932.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89932.0, "min": 29952.0, "max": 89932.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09006470441818237, "min": -0.09006470441818237, "max": -0.05955871567130089, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -21.795658111572266, "min": -21.795658111572266, "max": -14.115415573120117, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.18890169262886047, "min": 0.18890169262886047, "max": 0.2630091607570648, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 45.714210510253906, "min": 45.714210510253906, "max": 63.12220001220703, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06750146815703881, "min": 0.06750146815703881, "max": 0.07170572742287984, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.6075132134133493, "min": 0.4972169131273738, "max": 0.6075132134133493, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.001913338231602507, "min": 0.0006711106492034387, "max": 0.007311663421230983, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.017220044084422563, "min": 0.004697774544424071, "max": 0.05118164394861688, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.353807548733332e-05, "min": 7.353807548733332e-05, "max": 0.0002515063018788571, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0006618426793859999, "min": 0.0006618426793859999, "max": 0.0017605441131519997, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12451266666666665, "min": 0.12451266666666665, "max": 0.1838354285714286, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.1206139999999998, "min": 1.0911359999999999, "max": 1.2868480000000002, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.0024588153999999997, "min": 0.0024588153999999997, "max": 0.008385159314285713, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.0221293386, "min": 0.0221293386, "max": 0.058696115199999996, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.1146935522556305, "min": 0.1146935522556305, "max": 0.3848760426044464, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.032241940498352, "min": 1.032241940498352, "max": 2.6941323280334473, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 965.0, "min": 965.0, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32810.0, "min": 15984.0, "max": 32810.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8482941678341698, "min": -1.0000000521540642, "max": -0.8482941678341698, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -28.84200170636177, "min": -32.000001668930054, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8482941678341698, "min": -1.0000000521540642, "max": -0.8482941678341698, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -28.84200170636177, "min": -32.000001668930054, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 1.282595489612397, "min": 1.282595489612397, "max": 7.8693959303200245, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 43.6082466468215, "min": 43.6082466468215, "max": 125.91033488512039, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688446931", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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 --no-graphics", "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": "1688447238" }, "total": 306.71329099, "count": 1, "self": 0.5929661990000454, "children": { "run_training.setup": { "total": 0.07925935099996195, "count": 1, "self": 0.07925935099996195 }, "TrainerController.start_learning": { "total": 306.04106544, "count": 1, "self": 0.22349967699477702, "children": { "TrainerController._reset_env": { "total": 2.4367131839999843, "count": 1, "self": 2.4367131839999843 }, "TrainerController.advance": { "total": 303.1775318450052, "count": 6274, "self": 0.2226084700089359, "children": { "env_step": { "total": 181.76730748699606, "count": 6274, "self": 167.47458686099338, "children": { "SubprocessEnvManager._take_step": { "total": 14.16453502399645, "count": 6274, "self": 0.7265861139967456, "children": { "TorchPolicy.evaluate": { "total": 13.437948909999704, "count": 6273, "self": 13.437948909999704 } } }, "workers": { "total": 0.12818560200622642, "count": 6274, "self": 0.0, "children": { "worker_root": { "total": 305.22412085699875, "count": 6274, "is_parallel": true, "self": 154.28084327300417, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009090148000041154, "count": 1, "is_parallel": true, "self": 0.00658057300006476, "children": { "_process_rank_one_or_two_observation": { "total": 0.002509574999976394, "count": 8, "is_parallel": true, "self": 0.002509574999976394 } } }, "UnityEnvironment.step": { "total": 0.1149101880000103, "count": 1, "is_parallel": true, "self": 0.0007011060000650104, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005416999999852123, "count": 1, "is_parallel": true, "self": 0.0005416999999852123 }, "communicator.exchange": { "total": 0.11118800499997405, "count": 1, "is_parallel": true, "self": 0.11118800499997405 }, "steps_from_proto": { "total": 0.002479376999986016, "count": 1, "is_parallel": true, "self": 0.0005794629998945311, "children": { "_process_rank_one_or_two_observation": { "total": 0.001899914000091485, "count": 8, "is_parallel": true, "self": 0.001899914000091485 } } } } } } }, "UnityEnvironment.step": { "total": 150.9432775839946, "count": 6273, "is_parallel": true, "self": 4.536070188996064, "children": { "UnityEnvironment._generate_step_input": { "total": 2.499008301996014, "count": 6273, "is_parallel": true, "self": 2.499008301996014 }, "communicator.exchange": { "total": 129.7867365439971, "count": 6273, "is_parallel": true, "self": 129.7867365439971 }, "steps_from_proto": { "total": 14.1214625490054, "count": 6273, "is_parallel": true, "self": 2.9101510599992935, "children": { "_process_rank_one_or_two_observation": { "total": 11.211311489006107, "count": 50184, "is_parallel": true, "self": 11.211311489006107 } } } } } } } } } } }, "trainer_advance": { "total": 121.18761588800021, "count": 6274, "self": 0.2707400959995425, "children": { "process_trajectory": { "total": 14.648106904000883, "count": 6274, "self": 14.648106904000883 }, "_update_policy": { "total": 106.26876888799978, "count": 27, "self": 44.46207379600054, "children": { "TorchPPOOptimizer.update": { "total": 61.806695091999245, "count": 2337, "self": 61.806695091999245 } } } } } } }, "trainer_threads": { "total": 1.0620000239214278e-06, "count": 1, "self": 1.0620000239214278e-06 }, "TrainerController._save_models": { "total": 0.20331967200002055, "count": 1, "self": 0.0017556590000822325, "children": { "RLTrainer._checkpoint": { "total": 0.2015640129999383, "count": 1, "self": 0.2015640129999383 } } } } } } }