{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3096799850463867, "min": 0.2793619632720947, "max": 1.3872404098510742, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9364.72265625, "min": 8354.0400390625, "max": 42083.32421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989973.0, "min": 29952.0, "max": 989973.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989973.0, "min": 29952.0, "max": 989973.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.656428337097168, "min": -0.17696113884449005, "max": 0.6687299609184265, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 185.11279296875, "min": -41.939788818359375, "max": 190.58804321289062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03270343691110611, "min": 0.012618501670658588, "max": 0.42579877376556396, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.222369194030762, "min": 3.470088005065918, "max": 102.61750793457031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0678897350464024, "min": 0.06511024951821334, "max": 0.0746426832075009, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9504562906496337, "min": 0.5054788357944859, "max": 1.0624607114781004, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015211266924216899, "min": 0.002216983608685267, "max": 0.01794845756202925, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21295773693903658, "min": 0.027585812251779425, "max": 0.2540822915810471, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.410118958564288e-06, "min": 7.410118958564288e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010374166541990003, "min": 0.00010374166541990003, "max": 0.0036333679888773994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247000714285716, "min": 0.10247000714285716, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345801000000002, "min": 1.3886848, "max": 2.6111226000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002567537135714286, "min": 0.0002567537135714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035945519900000005, "min": 0.0035945519900000005, "max": 0.12113114774, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.024379415437579155, "min": 0.024379415437579155, "max": 0.6201043725013733, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.34131181240081787, "min": 0.34131181240081787, "max": 4.340730667114258, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 296.0388349514563, "min": 270.4403669724771, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30492.0, "min": 15984.0, "max": 32716.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6651184323053916, "min": -1.0000000521540642, "max": 1.7112073302268982, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 171.50719852745533, "min": -28.194201722741127, "max": 186.5215989947319, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6651184323053916, "min": -1.0000000521540642, "max": 1.7112073302268982, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 171.50719852745533, "min": -28.194201722741127, "max": 186.5215989947319, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07385458685067772, "min": 0.06985821303346061, "max": 12.852327389642596, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 7.607022445619805, "min": 7.335112368513364, "max": 205.63723823428154, "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": "1752840415", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1752842669" }, "total": 2254.421965914, "count": 1, "self": 0.47611952299985205, "children": { "run_training.setup": { "total": 0.019441674000063358, "count": 1, "self": 0.019441674000063358 }, "TrainerController.start_learning": { "total": 2253.926404717, "count": 1, "self": 1.2944124129780903, "children": { "TrainerController._reset_env": { "total": 2.1088751380000303, "count": 1, "self": 2.1088751380000303 }, "TrainerController.advance": { "total": 2250.4432504270217, "count": 64322, "self": 1.3666318040650367, "children": { "env_step": { "total": 1601.108532186966, "count": 64322, "self": 1455.6932741629087, "children": { "SubprocessEnvManager._take_step": { "total": 144.62869656201315, "count": 64322, "self": 4.62467940898955, "children": { "TorchPolicy.evaluate": { "total": 140.0040171530236, "count": 62556, "self": 140.0040171530236 } } }, "workers": { "total": 0.7865614620441193, "count": 64322, "self": 0.0, "children": { "worker_root": { "total": 2248.804912775011, "count": 64322, "is_parallel": true, "self": 903.1841769819569, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018405759999495785, "count": 1, "is_parallel": true, "self": 0.0005950439997377543, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012455320002118242, "count": 8, "is_parallel": true, "self": 0.0012455320002118242 } } }, "UnityEnvironment.step": { "total": 0.04559179099987887, "count": 1, "is_parallel": true, "self": 0.0005288520001158759, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000436012999898594, "count": 1, "is_parallel": true, "self": 0.000436012999898594 }, "communicator.exchange": { "total": 0.043086947999881886, "count": 1, "is_parallel": true, "self": 0.043086947999881886 }, "steps_from_proto": { "total": 0.0015399779999825114, "count": 1, "is_parallel": true, "self": 0.0003256130000863777, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012143649998961337, "count": 8, "is_parallel": true, "self": 0.0012143649998961337 } } } } } } }, "UnityEnvironment.step": { "total": 1345.620735793054, "count": 64321, "is_parallel": true, "self": 31.667817081070552, "children": { "UnityEnvironment._generate_step_input": { "total": 23.171008533987106, "count": 64321, "is_parallel": true, "self": 23.171008533987106 }, "communicator.exchange": { "total": 1195.4324573280396, "count": 64321, "is_parallel": true, "self": 1195.4324573280396 }, "steps_from_proto": { "total": 95.34945284995683, "count": 64321, "is_parallel": true, "self": 19.018691529006446, "children": { "_process_rank_one_or_two_observation": { "total": 76.33076132095039, "count": 514568, "is_parallel": true, "self": 76.33076132095039 } } } } } } } } } } }, "trainer_advance": { "total": 647.9680864359905, "count": 64322, "self": 2.5553399759564854, "children": { "process_trajectory": { "total": 125.81227176003654, "count": 64322, "self": 125.60525561403642, "children": { "RLTrainer._checkpoint": { "total": 0.20701614600011453, "count": 2, "self": 0.20701614600011453 } } }, "_update_policy": { "total": 519.6004746999974, "count": 458, "self": 290.74752111500266, "children": { "TorchPPOOptimizer.update": { "total": 228.8529535849948, "count": 22794, "self": 228.8529535849948 } } } } } } }, "trainer_threads": { "total": 1.032999989547534e-06, "count": 1, "self": 1.032999989547534e-06 }, "TrainerController._save_models": { "total": 0.07986570599996412, "count": 1, "self": 0.0014422729996113048, "children": { "RLTrainer._checkpoint": { "total": 0.07842343300035282, "count": 1, "self": 0.07842343300035282 } } } } } } }