{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1586179882287979, "min": 0.1544097363948822, "max": 1.337302803993225, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4750.92578125, "min": 4610.05712890625, "max": 40568.41796875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999915.0, "min": 29952.0, "max": 2999915.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999915.0, "min": 29952.0, "max": 2999915.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7369216084480286, "min": -0.09985122829675674, "max": 0.7753500938415527, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 214.44418334960938, "min": -23.66474151611328, "max": 228.728271484375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01092891301959753, "min": -0.03353351354598999, "max": 0.3911198079586029, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.1803135871887207, "min": -9.489984512329102, "max": 94.25987243652344, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06860520803336646, "min": 0.06419938498205004, "max": 0.07443041622101355, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9604729124671305, "min": 0.5210129135470949, "max": 1.0858304190566972, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012371604337441115, "min": 0.0002104063165885234, "max": 0.01578854657127522, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1732024607241756, "min": 0.0027352821156508044, "max": 0.23682819856912826, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4358138071428583e-06, "min": 1.4358138071428583e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0101393300000016e-05, "min": 2.0101393300000016e-05, "max": 0.0039690234769921996, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047857142857142, "min": 0.10047857142857142, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4066999999999998, "min": 1.3962282666666668, "max": 2.767501433333334, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.7809285714285755e-05, "min": 5.7809285714285755e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008093300000000006, "min": 0.0008093300000000006, "max": 0.13230847922, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00508119584992528, "min": 0.00508119584992528, "max": 0.6009030938148499, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07113674283027649, "min": 0.07113674283027649, "max": 4.206321716308594, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 261.3482142857143, "min": 235.75, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29271.0, "min": 15984.0, "max": 33627.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6850624844831015, "min": -1.0000000521540642, "max": 1.7473846044805315, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 188.72699826210737, "min": -31.993601635098457, "max": 226.22559739649296, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6850624844831015, "min": -1.0000000521540642, "max": 1.7473846044805315, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 188.72699826210737, "min": -31.993601635098457, "max": 226.22559739649296, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.013662784012589262, "min": 0.013299690477538206, "max": 11.602779211476445, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.5302318094099974, "min": 1.5302318094099974, "max": 185.64446738362312, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1700233442", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700241171" }, "total": 7728.327357268001, "count": 1, "self": 0.5955843860010646, "children": { "run_training.setup": { "total": 0.04176656100025866, "count": 1, "self": 0.04176656100025866 }, "TrainerController.start_learning": { "total": 7727.690006321, "count": 1, "self": 4.760127802766874, "children": { "TrainerController._reset_env": { "total": 3.4001895599999443, "count": 1, "self": 3.4001895599999443 }, "TrainerController.advance": { "total": 7719.447489961231, "count": 194355, "self": 4.948049133071436, "children": { "env_step": { "total": 5756.0320253511045, "count": 194355, "self": 5325.227589110141, "children": { "SubprocessEnvManager._take_step": { "total": 427.78664119311543, "count": 194355, "self": 14.942563248219358, "children": { "TorchPolicy.evaluate": { "total": 412.84407794489607, "count": 187562, "self": 412.84407794489607 } } }, "workers": { "total": 3.017795047848267, "count": 194355, "self": 0.0, "children": { "worker_root": { "total": 7710.845929996047, "count": 194355, "is_parallel": true, "self": 2790.695738591933, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002003913999942597, "count": 1, "is_parallel": true, "self": 0.000660605999200925, "children": { "_process_rank_one_or_two_observation": { "total": 0.001343308000741672, "count": 8, "is_parallel": true, "self": 0.001343308000741672 } } }, "UnityEnvironment.step": { "total": 0.04887549100021715, "count": 1, "is_parallel": true, "self": 0.0005450819999168743, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045937999993839185, "count": 1, "is_parallel": true, "self": 0.00045937999993839185 }, "communicator.exchange": { "total": 0.04612327600034405, "count": 1, "is_parallel": true, "self": 0.04612327600034405 }, "steps_from_proto": { "total": 0.0017477530000178376, "count": 1, "is_parallel": true, "self": 0.0003796559994952986, "children": { "_process_rank_one_or_two_observation": { "total": 0.001368097000522539, "count": 8, "is_parallel": true, "self": 0.001368097000522539 } } } } } } }, "UnityEnvironment.step": { "total": 4920.150191404114, "count": 194354, "is_parallel": true, "self": 107.6055153239131, "children": { "UnityEnvironment._generate_step_input": { "total": 76.5045600642934, "count": 194354, "is_parallel": true, "self": 76.5045600642934 }, "communicator.exchange": { "total": 4419.607522717985, "count": 194354, "is_parallel": true, "self": 4419.607522717985 }, "steps_from_proto": { "total": 316.4325932979218, "count": 194354, "is_parallel": true, "self": 66.91406591928444, "children": { "_process_rank_one_or_two_observation": { "total": 249.51852737863737, "count": 1554832, "is_parallel": true, "self": 249.51852737863737 } } } } } } } } } } }, "trainer_advance": { "total": 1958.467415477056, "count": 194355, "self": 9.515680843937844, "children": { "process_trajectory": { "total": 400.02643080511007, "count": 194355, "self": 399.4542136691098, "children": { "RLTrainer._checkpoint": { "total": 0.5722171360002903, "count": 6, "self": 0.5722171360002903 } } }, "_update_policy": { "total": 1548.925303828008, "count": 1399, "self": 926.5789469631422, "children": { "TorchPPOOptimizer.update": { "total": 622.3463568648658, "count": 68361, "self": 622.3463568648658 } } } } } } }, "trainer_threads": { "total": 1.1450010788394138e-06, "count": 1, "self": 1.1450010788394138e-06 }, "TrainerController._save_models": { "total": 0.08219785199980834, "count": 1, "self": 0.0015661960005672881, "children": { "RLTrainer._checkpoint": { "total": 0.08063165599924105, "count": 1, "self": 0.08063165599924105 } } } } } } }