{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7020999789237976, "min": 0.6669145822525024, "max": 1.441372036933899, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20973.130859375, "min": 20220.849609375, "max": 43725.4609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989896.0, "min": 29952.0, "max": 989896.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989896.0, "min": 29952.0, "max": 989896.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.037045639008283615, "min": -0.03178275749087334, "max": 0.040393684059381485, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 9.187318801879883, "min": -7.65964412689209, "max": 10.098421096801758, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014940005727112293, "min": 0.012862633913755417, "max": 0.2567141056060791, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.7051215171813965, "min": 3.1770706176757812, "max": 61.868099212646484, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06947535044621743, "min": 0.0643163189127766, "max": 0.07215988549675481, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.972654906247044, "min": 0.49437395653629873, "max": 1.0538223329668992, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0039354200188632775, "min": 6.786834661598733e-05, "max": 0.005722258433817397, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.055095880264085885, "min": 0.0008822885060078353, "max": 0.07501528168825411, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.699961719092857e-06, "min": 7.699961719092857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001077994640673, "min": 0.0001077994640673, "max": 0.0033820433726523005, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256662142857144, "min": 0.10256662142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359327000000002, "min": 1.3886848, "max": 2.5273477, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026640548071428576, "min": 0.00026640548071428576, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037296767300000005, "min": 0.0037296767300000005, "max": 0.11276203523, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013552534393966198, "min": 0.013552534393966198, "max": 0.43285655975341797, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18973548710346222, "min": 0.18973548710346222, "max": 3.029995918273926, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 762.5853658536586, "min": 744.7692307692307, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31266.0, "min": 15984.0, "max": 33117.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.310321903628547, "min": -1.0000000521540642, "max": 0.3343313917517662, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 12.723198048770428, "min": -30.996201619505882, "max": 12.943998403847218, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.310321903628547, "min": -1.0000000521540642, "max": 0.3343313917517662, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 12.723198048770428, "min": -30.996201619505882, "max": 12.943998403847218, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10850731182485683, "min": 0.10850731182485683, "max": 8.517358732409775, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.44879978481913, "min": 4.078956481418572, "max": 136.2777397185564, "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": "1702130448", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --force --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702132568" }, "total": 2119.6748776659997, "count": 1, "self": 0.47745845999907033, "children": { "run_training.setup": { "total": 0.054103598999972746, "count": 1, "self": 0.054103598999972746 }, "TrainerController.start_learning": { "total": 2119.1433156070007, "count": 1, "self": 1.391120245930324, "children": { "TrainerController._reset_env": { "total": 3.0102920459994493, "count": 1, "self": 3.0102920459994493 }, "TrainerController.advance": { "total": 2114.6646633120727, "count": 63293, "self": 1.3891991430709822, "children": { "env_step": { "total": 1472.0262961130138, "count": 63293, "self": 1341.4284911729856, "children": { "SubprocessEnvManager._take_step": { "total": 129.76438847602185, "count": 63293, "self": 4.596129612904406, "children": { "TorchPolicy.evaluate": { "total": 125.16825886311744, "count": 62565, "self": 125.16825886311744 } } }, "workers": { "total": 0.8334164640064046, "count": 63293, "self": 0.0, "children": { "worker_root": { "total": 2114.5560418550776, "count": 63293, "is_parallel": true, "self": 889.5922931840805, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019031969995921827, "count": 1, "is_parallel": true, "self": 0.0006062219999876106, "children": { "_process_rank_one_or_two_observation": { "total": 0.001296974999604572, "count": 8, "is_parallel": true, "self": 0.001296974999604572 } } }, "UnityEnvironment.step": { "total": 0.0455779750000147, "count": 1, "is_parallel": true, "self": 0.0005535700011023437, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046830599967506714, "count": 1, "is_parallel": true, "self": 0.00046830599967506714 }, "communicator.exchange": { "total": 0.042940239000017755, "count": 1, "is_parallel": true, "self": 0.042940239000017755 }, "steps_from_proto": { "total": 0.0016158599992195377, "count": 1, "is_parallel": true, "self": 0.0003550369974618661, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012608230017576716, "count": 8, "is_parallel": true, "self": 0.0012608230017576716 } } } } } } }, "UnityEnvironment.step": { "total": 1224.9637486709971, "count": 63292, "is_parallel": true, "self": 34.30147354429391, "children": { "UnityEnvironment._generate_step_input": { "total": 24.1876479599714, "count": 63292, "is_parallel": true, "self": 24.1876479599714 }, "communicator.exchange": { "total": 1069.7211497728022, "count": 63292, "is_parallel": true, "self": 1069.7211497728022 }, "steps_from_proto": { "total": 96.75347739392964, "count": 63292, "is_parallel": true, "self": 19.17364639160496, "children": { "_process_rank_one_or_two_observation": { "total": 77.57983100232468, "count": 506336, "is_parallel": true, "self": 77.57983100232468 } } } } } } } } } } }, "trainer_advance": { "total": 641.2491680559879, "count": 63293, "self": 2.5166844681061775, "children": { "process_trajectory": { "total": 125.04373812987978, "count": 63293, "self": 124.86157563687993, "children": { "RLTrainer._checkpoint": { "total": 0.18216249299985066, "count": 2, "self": 0.18216249299985066 } } }, "_update_policy": { "total": 513.6887454580019, "count": 445, "self": 308.09642751698175, "children": { "TorchPPOOptimizer.update": { "total": 205.59231794102016, "count": 22746, "self": 205.59231794102016 } } } } } } }, "trainer_threads": { "total": 9.449995559407398e-07, "count": 1, "self": 9.449995559407398e-07 }, "TrainerController._save_models": { "total": 0.0772390579986677, "count": 1, "self": 0.0017312479976681061, "children": { "RLTrainer._checkpoint": { "total": 0.0755078100009996, "count": 1, "self": 0.0755078100009996 } } } } } } }