{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35659268498420715, "min": 0.35659268498420715, "max": 1.4464179277420044, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10766.24609375, "min": 10766.24609375, "max": 43878.53515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989998.0, "min": 29952.0, "max": 989998.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989998.0, "min": 29952.0, "max": 989998.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5554537177085876, "min": -0.08762737363576889, "max": 0.5883548855781555, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 154.4161376953125, "min": -21.030569076538086, "max": 165.91607666015625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07612387835979462, "min": -0.0440775603055954, "max": 0.3590862452983856, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 21.162437438964844, "min": -11.283855438232422, "max": 85.10343933105469, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06769165315519622, "min": 0.06374670580167276, "max": 0.07148971865812183, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9476831441727471, "min": 0.5000597667509366, "max": 1.0687312037266299, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012951851048412556, "min": 0.0004213311831797018, "max": 0.015387932273105712, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18132591467777578, "min": 0.005477305381336123, "max": 0.21543105182347996, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.617418889464286e-06, "min": 7.617418889464286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010664386445250001, "min": 0.00010664386445250001, "max": 0.0034930540356486995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253910714285716, "min": 0.10253910714285716, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355475000000002, "min": 1.3886848, "max": 2.5276006000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026365680357142855, "min": 0.00026365680357142855, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00369119525, "min": 0.00369119525, "max": 0.11644869486999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012202026322484016, "min": 0.012049351818859577, "max": 0.5200421214103699, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17082837224006653, "min": 0.16869091987609863, "max": 3.6402950286865234, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 350.8780487804878, "min": 327.14606741573033, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28772.0, "min": 15984.0, "max": 33322.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5758268153522073, "min": -1.0000000521540642, "max": 1.6624130206587522, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 129.217798858881, "min": -31.996801674365997, "max": 152.9419979006052, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5758268153522073, "min": -1.0000000521540642, "max": 1.6624130206587522, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 129.217798858881, "min": -31.996801674365997, "max": 152.9419979006052, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04456620345391878, "min": 0.04192256064937722, "max": 11.078681353479624, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.65442868322134, "min": 3.65442868322134, "max": 177.25890165567398, "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": "1712944083", "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 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712946511" }, "total": 2427.5327057490003, "count": 1, "self": 0.5307231530000536, "children": { "run_training.setup": { "total": 0.08889312700011942, "count": 1, "self": 0.08889312700011942 }, "TrainerController.start_learning": { "total": 2426.913089469, "count": 1, "self": 1.5716157070332883, "children": { "TrainerController._reset_env": { "total": 2.290314542000033, "count": 1, "self": 2.290314542000033 }, "TrainerController.advance": { "total": 2422.959735101967, "count": 63809, "self": 1.6175734618341266, "children": { "env_step": { "total": 1766.398982187056, "count": 63809, "self": 1621.4609890211464, "children": { "SubprocessEnvManager._take_step": { "total": 143.93898208093697, "count": 63809, "self": 5.3297580839634975, "children": { "TorchPolicy.evaluate": { "total": 138.60922399697347, "count": 62575, "self": 138.60922399697347 } } }, "workers": { "total": 0.9990110849726079, "count": 63809, "self": 0.0, "children": { "worker_root": { "total": 2421.3830879441794, "count": 63809, "is_parallel": true, "self": 938.3398763641949, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002177285000016127, "count": 1, "is_parallel": true, "self": 0.0006832979993305344, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014939870006855926, "count": 8, "is_parallel": true, "self": 0.0014939870006855926 } } }, "UnityEnvironment.step": { "total": 0.04973701400012942, "count": 1, "is_parallel": true, "self": 0.0006779780005672364, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005907099998694321, "count": 1, "is_parallel": true, "self": 0.0005907099998694321 }, "communicator.exchange": { "total": 0.04643153300003178, "count": 1, "is_parallel": true, "self": 0.04643153300003178 }, "steps_from_proto": { "total": 0.0020367929996609746, "count": 1, "is_parallel": true, "self": 0.00043388699987190193, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016029059997890727, "count": 8, "is_parallel": true, "self": 0.0016029059997890727 } } } } } } }, "UnityEnvironment.step": { "total": 1483.0432115799845, "count": 63808, "is_parallel": true, "self": 38.22040997188196, "children": { "UnityEnvironment._generate_step_input": { "total": 27.009885376994134, "count": 63808, "is_parallel": true, "self": 27.009885376994134 }, "communicator.exchange": { "total": 1303.231241952009, "count": 63808, "is_parallel": true, "self": 1303.231241952009 }, "steps_from_proto": { "total": 114.58167427909939, "count": 63808, "is_parallel": true, "self": 23.90159641218588, "children": { "_process_rank_one_or_two_observation": { "total": 90.6800778669135, "count": 510464, "is_parallel": true, "self": 90.6800778669135 } } } } } } } } } } }, "trainer_advance": { "total": 654.9431794530769, "count": 63809, "self": 2.99216254615294, "children": { "process_trajectory": { "total": 137.06190282793023, "count": 63809, "self": 136.85910823292988, "children": { "RLTrainer._checkpoint": { "total": 0.20279459500034136, "count": 2, "self": 0.20279459500034136 } } }, "_update_policy": { "total": 514.8891140789938, "count": 452, "self": 303.8535244889631, "children": { "TorchPPOOptimizer.update": { "total": 211.03558959003067, "count": 22809, "self": 211.03558959003067 } } } } } } }, "trainer_threads": { "total": 1.038999471347779e-06, "count": 1, "self": 1.038999471347779e-06 }, "TrainerController._save_models": { "total": 0.0914230790003785, "count": 1, "self": 0.0016222490003201528, "children": { "RLTrainer._checkpoint": { "total": 0.08980083000005834, "count": 1, "self": 0.08980083000005834 } } } } } } }