{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2877524793148041, "min": 0.28037378191947937, "max": 1.4268958568572998, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8632.57421875, "min": 8456.0732421875, "max": 43286.3125, "count": 33 }, "Pyramids.Step.mean": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5826714038848877, "min": -0.12583427131175995, "max": 0.5826714038848877, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 158.4866180419922, "min": -29.822721481323242, "max": 158.4866180419922, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.018999353051185608, "min": -0.006691268179565668, "max": 0.40494099259376526, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.167823791503906, "min": -1.8534812927246094, "max": 95.97101593017578, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07045248707205953, "min": 0.06430401281724815, "max": 0.07267348802023525, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9863348190088335, "min": 0.49179285493493347, "max": 1.0181684526614845, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014117380960995926, "min": 0.00033836706874982957, "max": 0.01562855064188044, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19764333345394297, "min": 0.004737138962497614, "max": 0.21879970898632617, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.773161694692857e-06, "min": 7.773161694692857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010882426372570001, "min": 0.00010882426372570001, "max": 0.0037583905472031998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10259102142857145, "min": 0.10259102142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4362743000000002, "min": 1.3886848, "max": 2.6527968000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002688430407142858, "min": 0.0002688430407142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037638025700000013, "min": 0.0037638025700000013, "max": 0.12529440032000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01128899771720171, "min": 0.01128899771720171, "max": 0.3947899341583252, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1580459624528885, "min": 0.1580459624528885, "max": 2.7635295391082764, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 342.7469879518072, "min": 338.21590909090907, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28448.0, "min": 15984.0, "max": 33239.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6331493816820972, "min": -1.0000000521540642, "max": 1.6390477036210624, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 135.55139867961407, "min": -28.360401764512062, "max": 144.2361979186535, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6331493816820972, "min": -1.0000000521540642, "max": 1.6390477036210624, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 135.55139867961407, "min": -28.360401764512062, "max": 144.2361979186535, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04000767800432394, "min": 0.04000767800432394, "max": 7.642632808536291, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3206372743588872, "min": 3.3206372743588872, "max": 122.28212493658066, "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": "1743955083", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1743957345" }, "total": 2262.225471717, "count": 1, "self": 0.47718291900037, "children": { "run_training.setup": { "total": 0.02150538899991261, "count": 1, "self": 0.02150538899991261 }, "TrainerController.start_learning": { "total": 2261.726783409, "count": 1, "self": 1.3060752360024708, "children": { "TrainerController._reset_env": { "total": 2.3130046989999755, "count": 1, "self": 2.3130046989999755 }, "TrainerController.advance": { "total": 2258.0195997379974, "count": 63808, "self": 1.4055524070231513, "children": { "env_step": { "total": 1564.6132029320042, "count": 63808, "self": 1414.1606980620566, "children": { "SubprocessEnvManager._take_step": { "total": 149.727876925921, "count": 63808, "self": 4.721963372878008, "children": { "TorchPolicy.evaluate": { "total": 145.005913553043, "count": 62572, "self": 145.005913553043 } } }, "workers": { "total": 0.724627944026679, "count": 63808, "self": 0.0, "children": { "worker_root": { "total": 2256.806594267973, "count": 63808, "is_parallel": true, "self": 952.1751094809338, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021261609999783104, "count": 1, "is_parallel": true, "self": 0.0007156890001169813, "children": { "_process_rank_one_or_two_observation": { "total": 0.001410471999861329, "count": 8, "is_parallel": true, "self": 0.001410471999861329 } } }, "UnityEnvironment.step": { "total": 0.046081062999974165, "count": 1, "is_parallel": true, "self": 0.0006581170002846193, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042369499988126336, "count": 1, "is_parallel": true, "self": 0.00042369499988126336 }, "communicator.exchange": { "total": 0.042750522999995155, "count": 1, "is_parallel": true, "self": 0.042750522999995155 }, "steps_from_proto": { "total": 0.002248727999813127, "count": 1, "is_parallel": true, "self": 0.0007875389994751458, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014611890003379813, "count": 8, "is_parallel": true, "self": 0.0014611890003379813 } } } } } } }, "UnityEnvironment.step": { "total": 1304.6314847870394, "count": 63807, "is_parallel": true, "self": 31.887025870047637, "children": { "UnityEnvironment._generate_step_input": { "total": 23.021473815005265, "count": 63807, "is_parallel": true, "self": 23.021473815005265 }, "communicator.exchange": { "total": 1154.414487987994, "count": 63807, "is_parallel": true, "self": 1154.414487987994 }, "steps_from_proto": { "total": 95.30849711399242, "count": 63807, "is_parallel": true, "self": 18.760508781991348, "children": { "_process_rank_one_or_two_observation": { "total": 76.54798833200107, "count": 510456, "is_parallel": true, "self": 76.54798833200107 } } } } } } } } } } }, "trainer_advance": { "total": 692.00084439897, "count": 63808, "self": 2.5090417009432713, "children": { "process_trajectory": { "total": 128.66912971003057, "count": 63808, "self": 128.46520125703046, "children": { "RLTrainer._checkpoint": { "total": 0.20392845300011686, "count": 2, "self": 0.20392845300011686 } } }, "_update_policy": { "total": 560.8226729879962, "count": 455, "self": 308.77921890099196, "children": { "TorchPPOOptimizer.update": { "total": 252.0434540870042, "count": 22761, "self": 252.0434540870042 } } } } } } }, "trainer_threads": { "total": 1.1560000530153047e-06, "count": 1, "self": 1.1560000530153047e-06 }, "TrainerController._save_models": { "total": 0.08810257999994064, "count": 1, "self": 0.0014423010002246883, "children": { "RLTrainer._checkpoint": { "total": 0.08666027899971596, "count": 1, "self": 0.08666027899971596 } } } } } } }