{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4034603536128998, "min": 0.4034603536128998, "max": 1.441624402999878, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12116.7216796875, "min": 12116.7216796875, "max": 43733.1171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5509361624717712, "min": -0.10152972489595413, "max": 0.5711270570755005, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 153.16024780273438, "min": -24.36713409423828, "max": 157.63107299804688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01973814330995083, "min": -0.07092485576868057, "max": 0.28732559084892273, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.487203598022461, "min": -18.369537353515625, "max": 69.24546813964844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06712552360938902, "min": 0.0628926475946274, "max": 0.07364185182452784, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9397573305314462, "min": 0.5044845460021559, "max": 1.0494214753961584, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016175734406012353, "min": 0.00033806405714467507, "max": 0.017901110889053804, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22646028168417295, "min": 0.0043948327428807756, "max": 0.26851666333580704, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.2887475704499996e-06, "min": 7.2887475704499996e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001020424659863, "min": 0.0001020424659863, "max": 0.0035072795309069, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242955000000001, "min": 0.10242955000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340137000000002, "min": 1.3886848, "max": 2.5690930999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000252712045, "min": 0.000252712045, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035379686300000004, "min": 0.0035379686300000004, "max": 0.11693240069, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014060885645449162, "min": 0.013772127218544483, "max": 0.43179160356521606, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1968524008989334, "min": 0.19280977547168732, "max": 3.0225412845611572, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 343.3614457831325, "min": 314.71276595744683, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28499.0, "min": 15984.0, "max": 33356.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6101547438828718, "min": -1.0000000521540642, "max": 1.663047293661743, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 135.25299848616123, "min": -30.995801627635956, "max": 154.6633983105421, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6101547438828718, "min": -1.0000000521540642, "max": 1.663047293661743, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 135.25299848616123, "min": -30.995801627635956, "max": 154.6633983105421, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.049596969656011514, "min": 0.04547423213971929, "max": 7.828912867233157, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.166145451104967, "min": 3.8852962630116963, "max": 125.26260587573051, "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": "1680244170", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1680246456" }, "total": 2285.6837967740003, "count": 1, "self": 0.5379688220000389, "children": { "run_training.setup": { "total": 0.11177687700001115, "count": 1, "self": 0.11177687700001115 }, "TrainerController.start_learning": { "total": 2285.034051075, "count": 1, "self": 1.526752661045066, "children": { "TrainerController._reset_env": { "total": 3.7600357310000163, "count": 1, "self": 3.7600357310000163 }, "TrainerController.advance": { "total": 2279.6528434979555, "count": 63860, "self": 1.6228573990474615, "children": { "env_step": { "total": 1645.9014201989526, "count": 63860, "self": 1531.1015273039225, "children": { "SubprocessEnvManager._take_step": { "total": 113.86917124301726, "count": 63860, "self": 5.060746994019155, "children": { "TorchPolicy.evaluate": { "total": 108.80842424899811, "count": 62574, "self": 108.80842424899811 } } }, "workers": { "total": 0.930721652012835, "count": 63860, "self": 0.0, "children": { "worker_root": { "total": 2279.60542339595, "count": 63860, "is_parallel": true, "self": 870.5829482299666, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018605099999149388, "count": 1, "is_parallel": true, "self": 0.0006116000006386457, "children": { "_process_rank_one_or_two_observation": { "total": 0.001248909999276293, "count": 8, "is_parallel": true, "self": 0.001248909999276293 } } }, "UnityEnvironment.step": { "total": 0.05259518599996227, "count": 1, "is_parallel": true, "self": 0.0005603710001196305, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005115239998758625, "count": 1, "is_parallel": true, "self": 0.0005115239998758625 }, "communicator.exchange": { "total": 0.049780899999859685, "count": 1, "is_parallel": true, "self": 0.049780899999859685 }, "steps_from_proto": { "total": 0.0017423910001070908, "count": 1, "is_parallel": true, "self": 0.0003896430000622786, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013527480000448122, "count": 8, "is_parallel": true, "self": 0.0013527480000448122 } } } } } } }, "UnityEnvironment.step": { "total": 1409.0224751659832, "count": 63859, "is_parallel": true, "self": 33.824395202834694, "children": { "UnityEnvironment._generate_step_input": { "total": 25.082891923048464, "count": 63859, "is_parallel": true, "self": 25.082891923048464 }, "communicator.exchange": { "total": 1247.873811900054, "count": 63859, "is_parallel": true, "self": 1247.873811900054 }, "steps_from_proto": { "total": 102.24137614004599, "count": 63859, "is_parallel": true, "self": 22.230684701074324, "children": { "_process_rank_one_or_two_observation": { "total": 80.01069143897166, "count": 510872, "is_parallel": true, "self": 80.01069143897166 } } } } } } } } } } }, "trainer_advance": { "total": 632.1285658999554, "count": 63860, "self": 2.748148533954918, "children": { "process_trajectory": { "total": 114.86061282700689, "count": 63860, "self": 114.64977990700686, "children": { "RLTrainer._checkpoint": { "total": 0.21083292000002984, "count": 2, "self": 0.21083292000002984 } } }, "_update_policy": { "total": 514.5198045389936, "count": 453, "self": 330.5265650810013, "children": { "TorchPPOOptimizer.update": { "total": 183.99323945799233, "count": 22848, "self": 183.99323945799233 } } } } } } }, "trainer_threads": { "total": 1.1180000001331791e-06, "count": 1, "self": 1.1180000001331791e-06 }, "TrainerController._save_models": { "total": 0.0944180669994239, "count": 1, "self": 0.0013269269993543276, "children": { "RLTrainer._checkpoint": { "total": 0.09309114000006957, "count": 1, "self": 0.09309114000006957 } } } } } } }