{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.34091535210609436, "min": 0.34091535210609436, "max": 1.4090862274169922, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10156.5498046875, "min": 10156.5498046875, "max": 42746.0390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6467151641845703, "min": -0.15591514110565186, "max": 0.772113025188446, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 182.37367248535156, "min": -36.95188903808594, "max": 225.45700073242188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009000839665532112, "min": -0.017589855939149857, "max": 0.5911825299263, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.5382368564605713, "min": -4.731671333312988, "max": 140.11026000976562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06477477621570844, "min": 0.06477477621570844, "max": 0.07374250479291991, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9068468670199182, "min": 0.4881925151797799, "max": 1.0622135187344004, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014659599180540673, "min": 0.0005627853321240305, "max": 0.022153719489042174, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20523438852756942, "min": 0.0050650679891162745, "max": 0.23862027561214438, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.379583254457143e-06, "min": 7.379583254457143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001033141655624, "min": 0.0001033141655624, "max": 0.0032556353147883, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245982857142856, "min": 0.10245982857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344375999999999, "min": 1.3886848, "max": 2.4839565000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002557368742857143, "min": 0.0002557368742857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00358031624, "min": 0.00358031624, "max": 0.10854264883, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01100960187613964, "min": 0.01100960187613964, "max": 0.686024010181427, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15413442254066467, "min": 0.15413442254066467, "max": 4.802167892456055, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 282.8137254901961, "min": 238.79032258064515, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28847.0, "min": 15984.0, "max": 32634.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6983039005860394, "min": -1.0000000521540642, "max": 1.7611199892759324, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 173.22699785977602, "min": -30.99940161406994, "max": 220.13999865949154, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6983039005860394, "min": -1.0000000521540642, "max": 1.7611199892759324, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 173.22699785977602, "min": -30.99940161406994, "max": 220.13999865949154, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.032053829398886166, "min": 0.027995976618025453, "max": 15.889149049296975, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2694905986863887, "min": 3.2612519445538055, "max": 254.2263847887516, "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": "1714655733", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/elisa/Progetti/AI/004_ML_Agents/.venv3-10/bin/mlagents-learn ../ml-agents/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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714657221" }, "total": 1487.9123955459982, "count": 1, "self": 0.3214896429963119, "children": { "run_training.setup": { "total": 0.017530009001347935, "count": 1, "self": 0.017530009001347935 }, "TrainerController.start_learning": { "total": 1487.5733758940005, "count": 1, "self": 0.9090581061682315, "children": { "TrainerController._reset_env": { "total": 6.037889021998126, "count": 1, "self": 6.037889021998126 }, "TrainerController.advance": { "total": 1480.5275543188327, "count": 64355, "self": 0.9643198955382104, "children": { "env_step": { "total": 961.0776695898712, "count": 64355, "self": 747.0667560532493, "children": { "SubprocessEnvManager._take_step": { "total": 213.38195556967185, "count": 64355, "self": 2.960047013035364, "children": { "TorchPolicy.evaluate": { "total": 210.42190855663648, "count": 62548, "self": 210.42190855663648 } } }, "workers": { "total": 0.6289579669501109, "count": 64355, "self": 0.0, "children": { "worker_root": { "total": 1485.2003624943245, "count": 64355, "is_parallel": true, "self": 798.2961456802259, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00233853600002476, "count": 1, "is_parallel": true, "self": 0.00045393300024443306, "children": { "_process_rank_one_or_two_observation": { "total": 0.001884602999780327, "count": 8, "is_parallel": true, "self": 0.001884602999780327 } } }, "UnityEnvironment.step": { "total": 0.030638483000075212, "count": 1, "is_parallel": true, "self": 0.0002029999996011611, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003442739980528131, "count": 1, "is_parallel": true, "self": 0.0003442739980528131 }, "communicator.exchange": { "total": 0.029546964000473963, "count": 1, "is_parallel": true, "self": 0.029546964000473963 }, "steps_from_proto": { "total": 0.0005442450019472744, "count": 1, "is_parallel": true, "self": 0.00016445800429210067, "children": { "_process_rank_one_or_two_observation": { "total": 0.00037978699765517376, "count": 8, "is_parallel": true, "self": 0.00037978699765517376 } } } } } } }, "UnityEnvironment.step": { "total": 686.9042168140986, "count": 64354, "is_parallel": true, "self": 10.256480481944891, "children": { "UnityEnvironment._generate_step_input": { "total": 6.893933983286843, "count": 64354, "is_parallel": true, "self": 6.893933983286843 }, "communicator.exchange": { "total": 642.8569915760309, "count": 64354, "is_parallel": true, "self": 642.8569915760309 }, "steps_from_proto": { "total": 26.896810772836034, "count": 64354, "is_parallel": true, "self": 6.382040064574539, "children": { "_process_rank_one_or_two_observation": { "total": 20.514770708261494, "count": 514832, "is_parallel": true, "self": 20.514770708261494 } } } } } } } } } } }, "trainer_advance": { "total": 518.4855648334233, "count": 64355, "self": 1.7356253515463322, "children": { "process_trajectory": { "total": 97.47394687087944, "count": 64355, "self": 97.23722306687705, "children": { "RLTrainer._checkpoint": { "total": 0.2367238040023949, "count": 2, "self": 0.2367238040023949 } } }, "_update_policy": { "total": 419.2759926109975, "count": 448, "self": 175.37882802073, "children": { "TorchPPOOptimizer.update": { "total": 243.8971645902675, "count": 22875, "self": 243.8971645902675 } } } } } } }, "trainer_threads": { "total": 6.039990694262087e-07, "count": 1, "self": 6.039990694262087e-07 }, "TrainerController._save_models": { "total": 0.0988738430023659, "count": 1, "self": 0.000724806002835976, "children": { "RLTrainer._checkpoint": { "total": 0.09814903699952993, "count": 1, "self": 0.09814903699952993 } } } } } } }