{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.500912070274353, "min": 0.3842899799346924, "max": 1.2715579271316528, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14915.158203125, "min": 11510.25390625, "max": 38573.98046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04680251330137253, "min": -0.138963982462883, "max": -0.010420084930956364, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -11.326208114624023, "min": -33.490318298339844, "max": -2.469560146331787, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.034952934831380844, "min": 0.0347578264772892, "max": 1.342178225517273, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.458610534667969, "min": 8.376636505126953, "max": 323.4649658203125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.03173274706681201, "min": 0.027556562922998434, "max": 0.037836738619218865, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.2855947236013081, "min": 0.20678933751205766, "max": 0.3470223737725367, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.003380700878035076, "min": 0.00039278654515569826, "max": 0.048921443799155806, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.030426307902315684, "min": 0.0027495058160898877, "max": 0.34245010659409064, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.473097508999998e-06, "min": 7.473097508999998e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 6.725787758099999e-05, "min": 6.725787758099999e-05, "max": 0.0022223904592032, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249100000000001, "min": 0.10249100000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.9224190000000001, "min": 0.9224190000000001, "max": 1.6249413000000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002588509, "min": 0.0002588509, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0023296581, "min": 0.0023296581, "max": 0.07408560032, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.03177092969417572, "min": 0.03177092969417572, "max": 1.912568211555481, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2859383523464203, "min": 0.2859383523464203, "max": 13.387977600097656, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 925.3125, "min": 876.6285714285714, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29610.0, "min": 15984.0, "max": 32502.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.48825004626996815, "min": -1.0000000521540642, "max": -0.30560576170682907, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -15.62400148063898, "min": -31.998801663517952, "max": -10.696201659739017, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.48825004626996815, "min": -1.0000000521540642, "max": -0.30560576170682907, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -15.62400148063898, "min": -31.998801663517952, "max": -10.696201659739017, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.30168876553943846, "min": 0.30168876553943846, "max": 18.093110345304012, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 9.65404049726203, "min": 9.65404049726203, "max": 547.2774064987898, "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": "1740129445", "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": "1740132105" }, "total": 2660.4937289590002, "count": 1, "self": 0.6414052879995324, "children": { "run_training.setup": { "total": 0.04205247599998074, "count": 1, "self": 0.04205247599998074 }, "TrainerController.start_learning": { "total": 2659.8102711950005, "count": 1, "self": 2.2006106069593443, "children": { "TrainerController._reset_env": { "total": 2.8927381999999398, "count": 1, "self": 2.8927381999999398 }, "TrainerController.advance": { "total": 2654.632212687041, "count": 63168, "self": 2.3552786210429986, "children": { "env_step": { "total": 1851.0680143469897, "count": 63168, "self": 1691.553326659115, "children": { "SubprocessEnvManager._take_step": { "total": 158.19949582496224, "count": 63168, "self": 6.661595012989665, "children": { "TorchPolicy.evaluate": { "total": 151.53790081197258, "count": 62572, "self": 151.53790081197258 } } }, "workers": { "total": 1.315191862912343, "count": 63168, "self": 0.0, "children": { "worker_root": { "total": 2653.3484568629947, "count": 63168, "is_parallel": true, "self": 1121.029472078024, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002256515999988551, "count": 1, "is_parallel": true, "self": 0.0007363419997545861, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015201740002339648, "count": 8, "is_parallel": true, "self": 0.0015201740002339648 } } }, "UnityEnvironment.step": { "total": 0.07755939799994849, "count": 1, "is_parallel": true, "self": 0.000614622999819403, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000532859000031749, "count": 1, "is_parallel": true, "self": 0.000532859000031749 }, "communicator.exchange": { "total": 0.07444808300010664, "count": 1, "is_parallel": true, "self": 0.07444808300010664 }, "steps_from_proto": { "total": 0.0019638329999907, "count": 1, "is_parallel": true, "self": 0.0004743419999613252, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014894910000293748, "count": 8, "is_parallel": true, "self": 0.0014894910000293748 } } } } } } }, "UnityEnvironment.step": { "total": 1532.3189847849708, "count": 63167, "is_parallel": true, "self": 42.231405500977644, "children": { "UnityEnvironment._generate_step_input": { "total": 28.23809648102315, "count": 63167, "is_parallel": true, "self": 28.23809648102315 }, "communicator.exchange": { "total": 1340.4584376319974, "count": 63167, "is_parallel": true, "self": 1340.4584376319974 }, "steps_from_proto": { "total": 121.39104517097257, "count": 63167, "is_parallel": true, "self": 25.96464826406418, "children": { "_process_rank_one_or_two_observation": { "total": 95.4263969069084, "count": 505336, "is_parallel": true, "self": 95.4263969069084 } } } } } } } } } } }, "trainer_advance": { "total": 801.2089197190085, "count": 63168, "self": 4.110963655028172, "children": { "process_trajectory": { "total": 155.1501196459801, "count": 63168, "self": 154.8185532469804, "children": { "RLTrainer._checkpoint": { "total": 0.33156639899971196, "count": 2, "self": 0.33156639899971196 } } }, "_update_policy": { "total": 641.9478364180002, "count": 295, "self": 293.9863539670032, "children": { "TorchPPOOptimizer.update": { "total": 347.961482450997, "count": 5706, "self": 347.961482450997 } } } } } } }, "trainer_threads": { "total": 8.800002433417831e-07, "count": 1, "self": 8.800002433417831e-07 }, "TrainerController._save_models": { "total": 0.08470882099982191, "count": 1, "self": 0.002045196999461041, "children": { "RLTrainer._checkpoint": { "total": 0.08266362400036087, "count": 1, "self": 0.08266362400036087 } } } } } } }