{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48989957571029663, "min": 0.4866142272949219, "max": 1.465653657913208, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14665.6337890625, "min": 14520.568359375, "max": 44462.0703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5382402539253235, "min": -0.1050674244761467, "max": 0.5382402539253235, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 148.0160675048828, "min": -25.216182708740234, "max": 148.0160675048828, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.012010421603918076, "min": -0.014985104091465473, "max": 0.29222342371940613, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.302865982055664, "min": -4.090933322906494, "max": 70.42584228515625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06734731468133673, "min": 0.06528156414281028, "max": 0.07334840623653724, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9428624055387141, "min": 0.4972509099863036, "max": 1.0303699847330186, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014727176944558907, "min": 0.0002639110429302387, "max": 0.015401559833013122, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20618047722382468, "min": 0.0034308435580931032, "max": 0.21580296154385073, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.684640295628575e-06, "min": 7.684640295628575e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010758496413880004, "min": 0.00010758496413880004, "max": 0.003608956297014599, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256151428571429, "min": 0.10256151428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358612000000002, "min": 1.3886848, "max": 2.5692009999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002658952771428572, "min": 0.0002658952771428572, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003722533880000001, "min": 0.003722533880000001, "max": 0.12030824145999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012671798467636108, "min": 0.012671798467636108, "max": 0.4649715721607208, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17740517854690552, "min": 0.17740517854690552, "max": 3.254801034927368, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 340.61176470588236, "min": 340.61176470588236, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28952.0, "min": 15984.0, "max": 33887.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.565239985550151, "min": -1.0000000521540642, "max": 1.56653608671493, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 133.04539877176285, "min": -30.99500161409378, "max": 133.04539877176285, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.565239985550151, "min": -1.0000000521540642, "max": 1.56653608671493, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 133.04539877176285, "min": -30.99500161409378, "max": 133.04539877176285, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04503422758973423, "min": 0.04503422758973423, "max": 8.93597935512662, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8279093451274093, "min": 3.8279093451274093, "max": 142.9756696820259, "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": "1692293332", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1692295557" }, "total": 2224.6578828730003, "count": 1, "self": 0.4890370390003227, "children": { "run_training.setup": { "total": 0.06702134899990142, "count": 1, "self": 0.06702134899990142 }, "TrainerController.start_learning": { "total": 2224.101824485, "count": 1, "self": 1.4316630520602303, "children": { "TrainerController._reset_env": { "total": 4.4715583979999565, "count": 1, "self": 4.4715583979999565 }, "TrainerController.advance": { "total": 2218.09872981694, "count": 63638, "self": 1.485590734883317, "children": { "env_step": { "total": 1547.8207119430149, "count": 63638, "self": 1432.7389535329996, "children": { "SubprocessEnvManager._take_step": { "total": 114.18854082001133, "count": 63638, "self": 5.0765364539462325, "children": { "TorchPolicy.evaluate": { "total": 109.1120043660651, "count": 62544, "self": 109.1120043660651 } } }, "workers": { "total": 0.8932175900039283, "count": 63638, "self": 0.0, "children": { "worker_root": { "total": 2218.6789025749763, "count": 63638, "is_parallel": true, "self": 908.8188593189809, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005973347000008289, "count": 1, "is_parallel": true, "self": 0.004510955999990074, "children": { "_process_rank_one_or_two_observation": { "total": 0.001462391000018215, "count": 8, "is_parallel": true, "self": 0.001462391000018215 } } }, "UnityEnvironment.step": { "total": 0.050404595000031804, "count": 1, "is_parallel": true, "self": 0.0005798519999871132, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005567250000240165, "count": 1, "is_parallel": true, "self": 0.0005567250000240165 }, "communicator.exchange": { "total": 0.04738460800001576, "count": 1, "is_parallel": true, "self": 0.04738460800001576 }, "steps_from_proto": { "total": 0.0018834100000049148, "count": 1, "is_parallel": true, "self": 0.0003701380002212318, "children": { "_process_rank_one_or_two_observation": { "total": 0.001513271999783683, "count": 8, "is_parallel": true, "self": 0.001513271999783683 } } } } } } }, "UnityEnvironment.step": { "total": 1309.8600432559954, "count": 63637, "is_parallel": true, "self": 34.95198454792876, "children": { "UnityEnvironment._generate_step_input": { "total": 25.010780978022808, "count": 63637, "is_parallel": true, "self": 25.010780978022808 }, "communicator.exchange": { "total": 1137.9339000180248, "count": 63637, "is_parallel": true, "self": 1137.9339000180248 }, "steps_from_proto": { "total": 111.96337771201877, "count": 63637, "is_parallel": true, "self": 22.14405886602185, "children": { "_process_rank_one_or_two_observation": { "total": 89.81931884599692, "count": 509096, "is_parallel": true, "self": 89.81931884599692 } } } } } } } } } } }, "trainer_advance": { "total": 668.7924271390417, "count": 63638, "self": 2.6619493010548467, "children": { "process_trajectory": { "total": 118.25880635198519, "count": 63638, "self": 117.99045323198538, "children": { "RLTrainer._checkpoint": { "total": 0.2683531199998015, "count": 2, "self": 0.2683531199998015 } } }, "_update_policy": { "total": 547.8716714860017, "count": 451, "self": 358.64141225501555, "children": { "TorchPPOOptimizer.update": { "total": 189.23025923098612, "count": 22791, "self": 189.23025923098612 } } } } } } }, "trainer_threads": { "total": 1.252999936696142e-06, "count": 1, "self": 1.252999936696142e-06 }, "TrainerController._save_models": { "total": 0.09987196500014761, "count": 1, "self": 0.0014120720002210874, "children": { "RLTrainer._checkpoint": { "total": 0.09845989299992652, "count": 1, "self": 0.09845989299992652 } } } } } } }