{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.685166597366333, "min": 0.685166597366333, "max": 1.419629454612732, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20489.22265625, "min": 20489.22265625, "max": 43065.87890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29953.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29953.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3156487047672272, "min": -0.10825890302658081, "max": 0.3156487047672272, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 82.06866455078125, "min": -25.873878479003906, "max": 82.06866455078125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.026348501443862915, "min": 0.009412511251866817, "max": 0.48380589485168457, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.850610256195068, "min": 2.343715190887451, "max": 115.14580535888672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07035847760309324, "min": 0.06200672317797961, "max": 0.07542449167531695, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0553771640463987, "min": 0.5279714417272187, "max": 1.072569654259817, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012931843258701479, "min": 0.0004213994234683411, "max": 0.015496560546872139, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19397764888052219, "min": 0.005478192505088434, "max": 0.21695184765620995, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.509737496786669e-06, "min": 7.509737496786669e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011264606245180003, "min": 0.00011264606245180003, "max": 0.003506858631047199, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250321333333333, "min": 0.10250321333333333, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375482, "min": 1.3886848, "max": 2.5689528, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026007101200000007, "min": 0.00026007101200000007, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039010651800000015, "min": 0.0039010651800000015, "max": 0.11691838472, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010072293691337109, "min": 0.009759615175426006, "max": 0.48777836561203003, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15108440816402435, "min": 0.13663461804389954, "max": 3.4144484996795654, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 501.6111111111111, "min": 501.6111111111111, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27087.0, "min": 16752.0, "max": 33106.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1701490549878641, "min": -0.9999806972280625, "max": 1.2663386831841161, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 64.35819802433252, "min": -30.99940161406994, "max": 78.5129983574152, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1701490549878641, "min": -0.9999806972280625, "max": 1.2663386831841161, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 64.35819802433252, "min": -30.99940161406994, "max": 78.5129983574152, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.052619278847255785, "min": 0.052619278847255785, "max": 10.156325132531279, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8940603365990683, "min": 2.8940603365990683, "max": 172.65752725303173, "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": "1744039125", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1744042103" }, "total": 2977.616696759, "count": 1, "self": 0.6286547830004565, "children": { "run_training.setup": { "total": 0.03450483599999643, "count": 1, "self": 0.03450483599999643 }, "TrainerController.start_learning": { "total": 2976.9535371399998, "count": 1, "self": 2.28643439180496, "children": { "TrainerController._reset_env": { "total": 4.117762096000206, "count": 1, "self": 4.117762096000206 }, "TrainerController.advance": { "total": 2970.465557491195, "count": 63367, "self": 2.438857709284548, "children": { "env_step": { "total": 1988.2161449429968, "count": 63367, "self": 1835.3205516320581, "children": { "SubprocessEnvManager._take_step": { "total": 151.5908736349288, "count": 63367, "self": 6.7678281710336705, "children": { "TorchPolicy.evaluate": { "total": 144.82304546389514, "count": 62540, "self": 144.82304546389514 } } }, "workers": { "total": 1.3047196760098814, "count": 63367, "self": 0.0, "children": { "worker_root": { "total": 2969.735626051125, "count": 63367, "is_parallel": true, "self": 1299.736727972278, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0036806470002375136, "count": 1, "is_parallel": true, "self": 0.0013304349999998522, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023502120002376614, "count": 8, "is_parallel": true, "self": 0.0023502120002376614 } } }, "UnityEnvironment.step": { "total": 0.06579315599992697, "count": 1, "is_parallel": true, "self": 0.0006490329997177469, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005268449999675795, "count": 1, "is_parallel": true, "self": 0.0005268449999675795 }, "communicator.exchange": { "total": 0.06256441400000767, "count": 1, "is_parallel": true, "self": 0.06256441400000767 }, "steps_from_proto": { "total": 0.002052864000233967, "count": 1, "is_parallel": true, "self": 0.00042912599974442855, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016237380004895385, "count": 8, "is_parallel": true, "self": 0.0016237380004895385 } } } } } } }, "UnityEnvironment.step": { "total": 1669.998898078847, "count": 63366, "is_parallel": true, "self": 43.04045545472627, "children": { "UnityEnvironment._generate_step_input": { "total": 28.689100878008503, "count": 63366, "is_parallel": true, "self": 28.689100878008503 }, "communicator.exchange": { "total": 1479.1546869860285, "count": 63366, "is_parallel": true, "self": 1479.1546869860285 }, "steps_from_proto": { "total": 119.1146547600838, "count": 63366, "is_parallel": true, "self": 26.155536612298874, "children": { "_process_rank_one_or_two_observation": { "total": 92.95911814778492, "count": 506928, "is_parallel": true, "self": 92.95911814778492 } } } } } } } } } } }, "trainer_advance": { "total": 979.8105548389135, "count": 63367, "self": 4.338084858824004, "children": { "process_trajectory": { "total": 149.20144124008175, "count": 63367, "self": 148.99143462208167, "children": { "RLTrainer._checkpoint": { "total": 0.21000661800007947, "count": 2, "self": 0.21000661800007947 } } }, "_update_policy": { "total": 826.2710287400078, "count": 448, "self": 332.70615526509346, "children": { "TorchPPOOptimizer.update": { "total": 493.5648734749143, "count": 22752, "self": 493.5648734749143 } } } } } } }, "trainer_threads": { "total": 1.5579998944303952e-06, "count": 1, "self": 1.5579998944303952e-06 }, "TrainerController._save_models": { "total": 0.08378160299980664, "count": 1, "self": 0.0019976579997091903, "children": { "RLTrainer._checkpoint": { "total": 0.08178394500009745, "count": 1, "self": 0.08178394500009745 } } } } } } }