{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7847619652748108, "min": 0.6479609608650208, "max": 1.6092772483825684, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 2034.10302734375, "min": 1628.4112548828125, "max": 6591.599609375, "count": 100 }, "Pyramids.Step.mean": { "value": 299931.0, "min": 2944.0, "max": 299931.0, "count": 100 }, "Pyramids.Step.sum": { "value": 299931.0, "min": 2944.0, "max": 299931.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05807220935821533, "min": -0.12095541507005692, "max": -0.005570164415985346, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -1.393733024597168, "min": -2.7819745540618896, "max": -0.1336839497089386, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.031630128622055054, "min": 0.02453731931746006, "max": 0.5552518367767334, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.7591230869293213, "min": 0.5643583536148071, "max": 13.625702857971191, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.055871957913041115, "min": 0.05102754469650487, "max": 0.08809317380655557, "count": 93 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.055871957913041115, "min": 0.05102754469650487, "max": 0.15689841120996895, "count": 93 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.000732883921652198, "min": 8.441345554880779e-05, "max": 0.026324712671339512, "count": 93 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.000732883921652198, "min": 8.441345554880779e-05, "max": 0.026324712671339512, "count": 93 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.9410993529999924e-06, "min": 1.9410993529999924e-06, "max": 0.0002959040013653333, "count": 93 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.9410993529999924e-06, "min": 1.9410993529999924e-06, "max": 0.0005495170168276664, "count": 93 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.100647, "min": 0.100647, "max": 0.1986346666666667, "count": 93 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.100647, "min": 0.100647, "max": 0.38317233333333334, "count": 93 }, "Pyramids.Policy.Beta.mean": { "value": 7.463529999999976e-05, "min": 7.463529999999976e-05, "max": 0.009863603200000001, "count": 93 }, "Pyramids.Policy.Beta.sum": { "value": 7.463529999999976e-05, "min": 7.463529999999976e-05, "max": 0.0183189161, "count": 93 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.031964268535375595, "min": 0.02736211195588112, "max": 1.0510932207107544, "count": 93 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.031964268535375595, "min": 0.028990933671593666, "max": 1.0510932207107544, "count": 93 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 401.0, "max": 999.0, "count": 67 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 1998.0, "min": 401.0, "max": 15984.0, "count": 67 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9994000494480133, "min": -1.0000000521540642, "max": 1.5990000218153, "count": 71 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -1.9988000988960266, "min": -15.000000782310963, "max": 1.5990000218153, "count": 71 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9994000494480133, "min": -1.0000000521540642, "max": 1.5990000218153, "count": 71 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -1.9988000988960266, "min": -15.000000782310963, "max": 1.5990000218153, "count": 71 }, "Pyramids.Policy.RndReward.mean": { "value": 0.30977628007531166, "min": 0.22260766476392746, "max": 10.41759622991085, "count": 71 }, "Pyramids.Policy.RndReward.sum": { "value": 0.6195525601506233, "min": 0.2707346919924021, "max": 104.1759622991085, "count": 71 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1748941189", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748941806" }, "total": 617.0286790299999, "count": 1, "self": 0.4810600030000387, "children": { "run_training.setup": { "total": 0.019883961000005, "count": 1, "self": 0.019883961000005 }, "TrainerController.start_learning": { "total": 616.5277350659999, "count": 1, "self": 0.37076961400862274, "children": { "TrainerController._reset_env": { "total": 2.492985835000127, "count": 1, "self": 2.492985835000127 }, "TrainerController.advance": { "total": 613.5527246979909, "count": 18872, "self": 0.40194259997315385, "children": { "env_step": { "total": 416.5144047480078, "count": 18872, "self": 371.90227803299376, "children": { "SubprocessEnvManager._take_step": { "total": 44.39193293299513, "count": 18872, "self": 1.3601010139930167, "children": { "TorchPolicy.evaluate": { "total": 43.031831919002116, "count": 18802, "self": 43.031831919002116 } } }, "workers": { "total": 0.22019378201889594, "count": 18872, "self": 0.0, "children": { "worker_root": { "total": 615.0778871489952, "count": 18872, "is_parallel": true, "self": 275.819031014998, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002103201999943849, "count": 1, "is_parallel": true, "self": 0.0007502850000946637, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013529169998491852, "count": 8, "is_parallel": true, "self": 0.0013529169998491852 } } }, "UnityEnvironment.step": { "total": 0.0945682310000393, "count": 1, "is_parallel": true, "self": 0.00057296399995721, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004552330001388327, "count": 1, "is_parallel": true, "self": 0.0004552330001388327 }, "communicator.exchange": { "total": 0.09196103599992966, "count": 1, "is_parallel": true, "self": 0.09196103599992966 }, "steps_from_proto": { "total": 0.0015789980000135984, "count": 1, "is_parallel": true, "self": 0.0003203600001597806, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012586379998538177, "count": 8, "is_parallel": true, "self": 0.0012586379998538177 } } } } } } }, "UnityEnvironment.step": { "total": 339.25885613399714, "count": 18871, "is_parallel": true, "self": 9.31283760995143, "children": { "UnityEnvironment._generate_step_input": { "total": 7.033624923023581, "count": 18871, "is_parallel": true, "self": 7.033624923023581 }, "communicator.exchange": { "total": 294.6270577600128, "count": 18871, "is_parallel": true, "self": 294.6270577600128 }, "steps_from_proto": { "total": 28.285335841009328, "count": 18871, "is_parallel": true, "self": 5.664750235977408, "children": { "_process_rank_one_or_two_observation": { "total": 22.62058560503192, "count": 150968, "is_parallel": true, "self": 22.62058560503192 } } } } } } } } } } }, "trainer_advance": { "total": 196.63637735000998, "count": 18872, "self": 0.5607021930161409, "children": { "process_trajectory": { "total": 37.016479805994095, "count": 18872, "self": 37.016479805994095 }, "_update_policy": { "total": 159.05919535099974, "count": 117, "self": 89.03164475100539, "children": { "TorchPPOOptimizer.update": { "total": 70.02755059999436, "count": 6858, "self": 70.02755059999436 } } } } } } }, "trainer_threads": { "total": 8.900001375877764e-07, "count": 1, "self": 8.900001375877764e-07 }, "TrainerController._save_models": { "total": 0.1112540290000652, "count": 1, "self": 0.0012828100000206177, "children": { "RLTrainer._checkpoint": { "total": 0.10997121900004458, "count": 1, "self": 0.10997121900004458 } } } } } } }