{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.10838235914707184, "min": 0.09950023889541626, "max": 1.5246258974075317, "count": 66 }, "Pyramids.Policy.Entropy.sum": { "value": 3287.88720703125, "min": 2981.8232421875, "max": 46251.05078125, "count": 66 }, "Pyramids.Step.mean": { "value": 1979902.0, "min": 29952.0, "max": 1979902.0, "count": 66 }, "Pyramids.Step.sum": { "value": 1979902.0, "min": 29952.0, "max": 1979902.0, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.78346186876297, "min": -0.0348844900727272, "max": 0.8182347416877747, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 231.12124633789062, "min": -8.407161712646484, "max": 246.28866577148438, "count": 66 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03988979011774063, "min": 0.027765318751335144, "max": 0.8566910624504089, "count": 66 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.767488479614258, "min": 8.19076919555664, "max": 203.03578186035156, "count": 66 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06973337994090148, "min": 0.06298405039318217, "max": 0.07285490355130575, "count": 66 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9762673191726207, "min": 0.4944924081544574, "max": 1.0610899953559663, "count": 66 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009280893576596144, "min": 0.0011239011363729627, "max": 0.03225873692536089, "count": 66 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.12993251007234602, "min": 0.010115110227356665, "max": 0.22581115847752622, "count": 66 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.1515804256964275e-06, "min": 5.1515804256964275e-06, "max": 0.0002975753150939428, "count": 66 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.212212595974998e-05, "min": 7.212212595974998e-05, "max": 0.0039795245234918505, "count": 66 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1, "min": 0.09999999999999996, "max": 0.10000000000000002, "count": 66 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4000000000000001, "min": 0.7, "max": 1.5000000000000002, "count": 66 }, "Pyramids.Policy.Beta.mean": { "value": 2.699989107142857e-05, "min": 2.699989107142857e-05, "max": 0.0009919985371428571, "count": 66 }, "Pyramids.Policy.Beta.sum": { "value": 0.000377998475, "min": 0.000377998475, "max": 0.013272430685000001, "count": 66 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.04242420941591263, "min": 0.04242420941591263, "max": 1.0313241481781006, "count": 66 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.593938946723938, "min": 0.593938946723938, "max": 7.219268798828125, "count": 66 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 229.6124031007752, "min": 215.93939393939394, "max": 999.0, "count": 66 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29620.0, "min": 15984.0, "max": 33105.0, "count": 66 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7548759521324506, "min": -1.0000000521540642, "max": 1.7840605914366967, "count": 66 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 226.37899782508612, "min": -28.205001778900623, "max": 239.27799846231937, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7548759521324506, "min": -1.0000000521540642, "max": 1.7840605914366967, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 226.37899782508612, "min": -28.205001778900623, "max": 239.27799846231937, "count": 66 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10055353927657065, "min": 0.09892512742027809, "max": 39.71318576578051, "count": 66 }, "Pyramids.Policy.RndReward.sum": { "value": 12.971406566677615, "min": 12.971406566677615, "max": 635.4109722524881, "count": 66 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1697030931", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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 Training7 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697035812" }, "total": 4880.286503290001, "count": 1, "self": 0.47867501100154186, "children": { "run_training.setup": { "total": 0.06616394900083833, "count": 1, "self": 0.06616394900083833 }, "TrainerController.start_learning": { "total": 4879.7416643299985, "count": 1, "self": 2.922324561943242, "children": { "TrainerController._reset_env": { "total": 4.117271718001575, "count": 1, "self": 4.117271718001575 }, "TrainerController.advance": { "total": 4872.580148277055, "count": 129796, "self": 2.95847217220944, "children": { "env_step": { "total": 3585.0640847292016, "count": 129796, "self": 3332.4309696495184, "children": { "SubprocessEnvManager._take_step": { "total": 250.96996573504111, "count": 129796, "self": 9.216337606583693, "children": { "TorchPolicy.evaluate": { "total": 241.75362812845742, "count": 125053, "self": 241.75362812845742 } } }, "workers": { "total": 1.663149344642079, "count": 129796, "self": 0.0, "children": { "worker_root": { "total": 4870.158710075988, "count": 129796, "is_parallel": true, "self": 1773.503997150825, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002491384000677499, "count": 1, "is_parallel": true, "self": 0.0007437559997924836, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017476280008850154, "count": 8, "is_parallel": true, "self": 0.0017476280008850154 } } }, "UnityEnvironment.step": { "total": 0.05994438500056276, "count": 1, "is_parallel": true, "self": 0.0006097460027376655, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046967599882918876, "count": 1, "is_parallel": true, "self": 0.00046967599882918876 }, "communicator.exchange": { "total": 0.057041281999772764, "count": 1, "is_parallel": true, "self": 0.057041281999772764 }, "steps_from_proto": { "total": 0.0018236809992231429, "count": 1, "is_parallel": true, "self": 0.00043842700142704416, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013852539977960987, "count": 8, "is_parallel": true, "self": 0.0013852539977960987 } } } } } } }, "UnityEnvironment.step": { "total": 3096.654712925163, "count": 129795, "is_parallel": true, "self": 68.39266053539359, "children": { "UnityEnvironment._generate_step_input": { "total": 46.88572312147335, "count": 129795, "is_parallel": true, "self": 46.88572312147335 }, "communicator.exchange": { "total": 2787.3074446792943, "count": 129795, "is_parallel": true, "self": 2787.3074446792943 }, "steps_from_proto": { "total": 194.06888458900175, "count": 129795, "is_parallel": true, "self": 38.87406657887732, "children": { "_process_rank_one_or_two_observation": { "total": 155.19481801012444, "count": 1038360, "is_parallel": true, "self": 155.19481801012444 } } } } } } } } } } }, "trainer_advance": { "total": 1284.5575913756438, "count": 129796, "self": 5.444389387534102, "children": { "process_trajectory": { "total": 246.93835949208733, "count": 129796, "self": 246.17243289408725, "children": { "RLTrainer._checkpoint": { "total": 0.7659265980000782, "count": 5, "self": 0.7659265980000782 } } }, "_update_policy": { "total": 1032.1748424960224, "count": 931, "self": 605.3518582801753, "children": { "TorchPPOOptimizer.update": { "total": 426.8229842158471, "count": 45573, "self": 426.8229842158471 } } } } } } }, "trainer_threads": { "total": 1.0879994079004973e-06, "count": 1, "self": 1.0879994079004973e-06 }, "TrainerController._save_models": { "total": 0.12191868499940028, "count": 1, "self": 0.0018928459994640434, "children": { "RLTrainer._checkpoint": { "total": 0.12002583899993624, "count": 1, "self": 0.12002583899993624 } } } } } } }