{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4029102027416229, "min": 0.4029102027416229, "max": 1.4100421667099, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11984.1611328125, "min": 11984.1611328125, "max": 42775.0390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989925.0, "min": 29952.0, "max": 989925.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989925.0, "min": 29952.0, "max": 989925.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4884537160396576, "min": -0.09977035224437714, "max": 0.5578473210334778, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 130.41714477539062, "min": -24.044654846191406, "max": 152.2923126220703, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00794416107237339, "min": -0.06432285904884338, "max": 0.4433222711086273, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.121090888977051, "min": -16.852588653564453, "max": 105.06737518310547, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06968139951932244, "min": 0.06647648767650022, "max": 0.07390834436483708, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0452209927898366, "min": 0.5173584105538596, "max": 1.063515145767608, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01477597832660346, "min": 0.00045809542192081404, "max": 0.01579551707409617, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2216396748990519, "min": 0.0059552404849705825, "max": 0.2216396748990519, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4887175037933375e-06, "min": 7.4887175037933375e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011233076255690006, "min": 0.00011233076255690006, "max": 0.0036073587975470997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249620666666667, "min": 0.10249620666666667, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374431000000002, "min": 1.3886848, "max": 2.5024529, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025937104600000014, "min": 0.00025937104600000014, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003890565690000002, "min": 0.003890565690000002, "max": 0.12025504471000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011630368418991566, "min": 0.011630368418991566, "max": 0.5577647686004639, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17445552349090576, "min": 0.16698484122753143, "max": 3.904353380203247, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 404.1168831168831, "min": 360.0120481927711, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31117.0, "min": 15984.0, "max": 34179.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4140051700078047, "min": -1.0000000521540642, "max": 1.589426165890126, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 108.87839809060097, "min": -28.461801551282406, "max": 133.51179793477058, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4140051700078047, "min": -1.0000000521540642, "max": 1.589426165890126, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 108.87839809060097, "min": -28.461801551282406, "max": 133.51179793477058, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04854380765169339, "min": 0.04563290999970169, "max": 11.997874394059181, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.737873189180391, "min": 3.6490858845063485, "max": 191.9659903049469, "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": "1722636546", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722638757" }, "total": 2210.9202578570003, "count": 1, "self": 0.4854052569999112, "children": { "run_training.setup": { "total": 0.051203347000182475, "count": 1, "self": 0.051203347000182475 }, "TrainerController.start_learning": { "total": 2210.383649253, "count": 1, "self": 1.6737539229952745, "children": { "TrainerController._reset_env": { "total": 1.9182995819999178, "count": 1, "self": 1.9182995819999178 }, "TrainerController.advance": { "total": 2206.7051235600043, "count": 63805, "self": 1.4780462649728179, "children": { "env_step": { "total": 1558.3454415030515, "count": 63805, "self": 1422.252772625154, "children": { "SubprocessEnvManager._take_step": { "total": 135.20659582798544, "count": 63805, "self": 4.834013486998174, "children": { "TorchPolicy.evaluate": { "total": 130.37258234098726, "count": 62569, "self": 130.37258234098726 } } }, "workers": { "total": 0.8860730499120564, "count": 63805, "self": 0.0, "children": { "worker_root": { "total": 2205.2659598550126, "count": 63805, "is_parallel": true, "self": 907.9879734470137, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002212514000120791, "count": 1, "is_parallel": true, "self": 0.0006893180002407462, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015231959998800448, "count": 8, "is_parallel": true, "self": 0.0015231959998800448 } } }, "UnityEnvironment.step": { "total": 0.04646817799994096, "count": 1, "is_parallel": true, "self": 0.000635707999663282, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048084700006256753, "count": 1, "is_parallel": true, "self": 0.00048084700006256753 }, "communicator.exchange": { "total": 0.04371758000002046, "count": 1, "is_parallel": true, "self": 0.04371758000002046 }, "steps_from_proto": { "total": 0.0016340430001946515, "count": 1, "is_parallel": true, "self": 0.0003493239998988429, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012847190002958087, "count": 8, "is_parallel": true, "self": 0.0012847190002958087 } } } } } } }, "UnityEnvironment.step": { "total": 1297.277986407999, "count": 63804, "is_parallel": true, "self": 33.53409468412292, "children": { "UnityEnvironment._generate_step_input": { "total": 22.611961521939293, "count": 63804, "is_parallel": true, "self": 22.611961521939293 }, "communicator.exchange": { "total": 1144.7105824439875, "count": 63804, "is_parallel": true, "self": 1144.7105824439875 }, "steps_from_proto": { "total": 96.4213477579492, "count": 63804, "is_parallel": true, "self": 19.58845370020299, "children": { "_process_rank_one_or_two_observation": { "total": 76.83289405774622, "count": 510432, "is_parallel": true, "self": 76.83289405774622 } } } } } } } } } } }, "trainer_advance": { "total": 646.8816357919798, "count": 63805, "self": 2.795837969938475, "children": { "process_trajectory": { "total": 128.7438471630412, "count": 63805, "self": 128.54943223604096, "children": { "RLTrainer._checkpoint": { "total": 0.19441492700025265, "count": 2, "self": 0.19441492700025265 } } }, "_update_policy": { "total": 515.3419506590001, "count": 453, "self": 306.70639192298427, "children": { "TorchPPOOptimizer.update": { "total": 208.6355587360158, "count": 22746, "self": 208.6355587360158 } } } } } } }, "trainer_threads": { "total": 6.568000571860466e-06, "count": 1, "self": 6.568000571860466e-06 }, "TrainerController._save_models": { "total": 0.08646562000012636, "count": 1, "self": 0.0018044509997707792, "children": { "RLTrainer._checkpoint": { "total": 0.08466116900035559, "count": 1, "self": 0.08466116900035559 } } } } } } }