{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15419848263263702, "min": 0.13651002943515778, "max": 0.823553740978241, "count": 80 }, "Pyramids.Policy.Entropy.sum": { "value": 4633.35595703125, "min": 3663.1669921875, "max": 24707.591796875, "count": 80 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 214.79136690647482, "min": 138.16666666666666, "max": 489.51666666666665, "count": 80 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29856.0, "min": 829.0, "max": 31776.0, "count": 80 }, "Pyramids.Step.mean": { "value": 2999909.0, "min": 629931.0, "max": 2999909.0, "count": 80 }, "Pyramids.Step.sum": { "value": 2999909.0, "min": 629931.0, "max": 2999909.0, "count": 80 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8359577655792236, "min": 0.25308457016944885, "max": 0.8370456695556641, "count": 80 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 248.27944946289062, "min": 8.604875564575195, "max": 252.99343872070312, "count": 80 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005533040966838598, "min": -0.01403752900660038, "max": 0.024144239723682404, "count": 80 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.6433131694793701, "min": -4.028770923614502, "max": 6.905252456665039, "count": 80 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7708172537654423, "min": 1.410446641842524, "max": 1.8618333041667938, "count": 80 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 246.1435982733965, "min": 11.170999825000763, "max": 246.1435982733965, "count": 80 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7708172537654423, "min": 1.410446641842524, "max": 1.8618333041667938, "count": 80 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 246.1435982733965, "min": 11.170999825000763, "max": 246.1435982733965, "count": 80 }, "Pyramids.Policy.RndReward.mean": { "value": 0.016907050741648826, "min": 0.014792351323800782, "max": 0.044656114225896694, "count": 80 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3500800530891865, "min": 0.0887541079428047, "max": 2.9113981585251167, "count": 80 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06731645511844814, "min": 0.06449578986689057, "max": 0.07284202956153811, "count": 80 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9424303716582739, "min": 0.06511365686310455, "max": 1.060511664133325, "count": 80 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015762173018168138, "min": 0.007312449966169273, "max": 0.016672092985356272, "count": 80 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22067042225435393, "min": 0.007312449966169273, "max": 0.24920289873261936, "count": 80 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4407423769285715e-06, "min": 1.4407423769285715e-06, "max": 0.00023719272093576668, "count": 80 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0170393277e-05, "min": 2.0170393277e-05, "max": 0.0035325708224765, "count": 80 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048021428571428, "min": 0.10048021428571428, "max": 0.17906423333333335, "count": 80 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.406723, "min": 0.17906423333333335, "max": 2.6775235000000004, "count": 80 }, "Pyramids.Policy.Beta.mean": { "value": 5.797340714285716e-05, "min": 5.797340714285716e-05, "max": 0.007908516909999998, "count": 80 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008116277000000002, "min": 0.0008116277000000002, "max": 0.11778459765000002, "count": 80 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0075660645961761475, "min": 0.007331254426389933, "max": 0.009189439006149769, "count": 80 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10592490434646606, "min": 0.008900578133761883, "max": 0.1329563856124878, "count": 80 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 80 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 80 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1726695630", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --resume --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": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1726704165" }, "total": 8535.375619375, "count": 1, "self": 0.7452478820014221, "children": { "run_training.setup": { "total": 0.08237167299967041, "count": 1, "self": 0.08237167299967041 }, "TrainerController.start_learning": { "total": 8534.547999819999, "count": 1, "self": 6.145169671061012, "children": { "TrainerController._reset_env": { "total": 3.3979853539999567, "count": 1, "self": 3.3979853539999567 }, "TrainerController.advance": { "total": 8524.909182714937, "count": 155171, "self": 6.299874070782607, "children": { "env_step": { "total": 5955.887078486949, "count": 155171, "self": 5576.892458963869, "children": { "SubprocessEnvManager._take_step": { "total": 375.4418779521029, "count": 155171, "self": 18.163601917177402, "children": { "TorchPolicy.evaluate": { "total": 357.2782760349255, "count": 148435, "self": 357.2782760349255 } } }, "workers": { "total": 3.55274157097665, "count": 155171, "self": 0.0, "children": { "worker_root": { "total": 8515.977976790391, "count": 155171, "is_parallel": true, "self": 3398.8017618879967, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003266829000040161, "count": 1, "is_parallel": true, "self": 0.001071900000624737, "children": { "_process_rank_one_or_two_observation": { "total": 0.002194928999415424, "count": 8, "is_parallel": true, "self": 0.002194928999415424 } } }, "UnityEnvironment.step": { "total": 0.06434809599977598, "count": 1, "is_parallel": true, "self": 0.0008171239992407209, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004978870001650648, "count": 1, "is_parallel": true, "self": 0.0004978870001650648 }, "communicator.exchange": { "total": 0.060996758000328555, "count": 1, "is_parallel": true, "self": 0.060996758000328555 }, "steps_from_proto": { "total": 0.002036327000041638, "count": 1, "is_parallel": true, "self": 0.00041612399991208804, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016202030001295498, "count": 8, "is_parallel": true, "self": 0.0016202030001295498 } } } } } } }, "UnityEnvironment.step": { "total": 5117.176214902394, "count": 155170, "is_parallel": true, "self": 120.9194205134263, "children": { "UnityEnvironment._generate_step_input": { "total": 72.63085866806523, "count": 155170, "is_parallel": true, "self": 72.63085866806523 }, "communicator.exchange": { "total": 4615.281839628038, "count": 155170, "is_parallel": true, "self": 4615.281839628038 }, "steps_from_proto": { "total": 308.34409609286513, "count": 155170, "is_parallel": true, "self": 68.52710665787299, "children": { "_process_rank_one_or_two_observation": { "total": 239.81698943499214, "count": 1241360, "is_parallel": true, "self": 239.81698943499214 } } } } } } } } } } }, "trainer_advance": { "total": 2562.7222301572065, "count": 155171, "self": 12.20619110042071, "children": { "process_trajectory": { "total": 410.9088252297897, "count": 155171, "self": 410.3971786137881, "children": { "RLTrainer._checkpoint": { "total": 0.5116466160015989, "count": 5, "self": 0.5116466160015989 } } }, "_update_policy": { "total": 2139.607213826996, "count": 1124, "self": 857.109888902974, "children": { "TorchPPOOptimizer.update": { "total": 1282.497324924022, "count": 54069, "self": 1282.497324924022 } } } } } } }, "trainer_threads": { "total": 1.2420005077729002e-06, "count": 1, "self": 1.2420005077729002e-06 }, "TrainerController._save_models": { "total": 0.09566083800018532, "count": 1, "self": 0.0034099340009561274, "children": { "RLTrainer._checkpoint": { "total": 0.0922509039992292, "count": 1, "self": 0.0922509039992292 } } } } } } }