{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.436708927154541, "min": 0.436708927154541, "max": 1.4847729206085205, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12954.533203125, "min": 12954.533203125, "max": 45042.0703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989977.0, "min": 29973.0, "max": 989977.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989977.0, "min": 29973.0, "max": 989977.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6345908641815186, "min": -0.09577009826898575, "max": 0.6345908641815186, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 180.8583984375, "min": -23.08059310913086, "max": 180.8583984375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.006815487053245306, "min": -0.0082451943308115, "max": 0.22189626097679138, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.9424138069152832, "min": -2.3004093170166016, "max": 52.811309814453125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07057803954036596, "min": 0.06581312956169545, "max": 0.07341554132775979, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0586705931054894, "min": 0.48492255972045334, "max": 1.0586705931054894, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015709134399852095, "min": 0.00010570143833803117, "max": 0.01590428139783047, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23563701599778142, "min": 0.0013741186983944052, "max": 0.23563701599778142, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.516917494393332e-06, "min": 7.516917494393332e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011275376241589998, "min": 0.00011275376241589998, "max": 0.003508122230626, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250560666666667, "min": 0.10250560666666667, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375841, "min": 1.3886848, "max": 2.569374, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026031010600000004, "min": 0.00026031010600000004, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039046515900000005, "min": 0.0039046515900000005, "max": 0.1169604626, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01208424661308527, "min": 0.01202623825520277, "max": 0.33760499954223633, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18126370012760162, "min": 0.16836734116077423, "max": 2.3632349967956543, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 301.54, "min": 291.9183673469388, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30154.0, "min": 16772.0, "max": 32483.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6984599857032299, "min": -0.9999097292461703, "max": 1.7080816173431825, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 169.845998570323, "min": -30.99720160663128, "max": 170.3315980732441, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6984599857032299, "min": -0.9999097292461703, "max": 1.7080816173431825, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 169.845998570323, "min": -30.99720160663128, "max": 170.3315980732441, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.037492200564011, "min": 0.03657792170878918, "max": 6.334871448686018, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.7492200564011, "min": 3.5846363274613395, "max": 107.6928146276623, "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": "1708801286", "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=Pyramids1 --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": "1708803588" }, "total": 2301.7093664510003, "count": 1, "self": 0.44490631200005737, "children": { "run_training.setup": { "total": 0.049827343000060864, "count": 1, "self": 0.049827343000060864 }, "TrainerController.start_learning": { "total": 2301.214632796, "count": 1, "self": 1.523024344071473, "children": { "TrainerController._reset_env": { "total": 3.726776722000068, "count": 1, "self": 3.726776722000068 }, "TrainerController.advance": { "total": 2295.8782966999283, "count": 63869, "self": 1.5501251139125998, "children": { "env_step": { "total": 1671.2855041770147, "count": 63869, "self": 1534.5279847220208, "children": { "SubprocessEnvManager._take_step": { "total": 135.86724715101195, "count": 63869, "self": 4.925555840919515, "children": { "TorchPolicy.evaluate": { "total": 130.94169131009244, "count": 62550, "self": 130.94169131009244 } } }, "workers": { "total": 0.8902723039818738, "count": 63869, "self": 0.0, "children": { "worker_root": { "total": 2296.115888033949, "count": 63869, "is_parallel": true, "self": 884.3640041219276, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005358784999998534, "count": 1, "is_parallel": true, "self": 0.003844972999559104, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015138120004394295, "count": 8, "is_parallel": true, "self": 0.0015138120004394295 } } }, "UnityEnvironment.step": { "total": 0.07786387999999533, "count": 1, "is_parallel": true, "self": 0.0006847429999652377, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005605999999716005, "count": 1, "is_parallel": true, "self": 0.0005605999999716005 }, "communicator.exchange": { "total": 0.07495934400003534, "count": 1, "is_parallel": true, "self": 0.07495934400003534 }, "steps_from_proto": { "total": 0.0016591930000231514, "count": 1, "is_parallel": true, "self": 0.0003364450003573438, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013227479996658076, "count": 8, "is_parallel": true, "self": 0.0013227479996658076 } } } } } } }, "UnityEnvironment.step": { "total": 1411.7518839120214, "count": 63868, "is_parallel": true, "self": 36.45216646202698, "children": { "UnityEnvironment._generate_step_input": { "total": 26.21164806999809, "count": 63868, "is_parallel": true, "self": 26.21164806999809 }, "communicator.exchange": { "total": 1242.4371790220027, "count": 63868, "is_parallel": true, "self": 1242.4371790220027 }, "steps_from_proto": { "total": 106.6508903579936, "count": 63868, "is_parallel": true, "self": 21.69000321302792, "children": { "_process_rank_one_or_two_observation": { "total": 84.96088714496568, "count": 510944, "is_parallel": true, "self": 84.96088714496568 } } } } } } } } } } }, "trainer_advance": { "total": 623.0426674090013, "count": 63869, "self": 2.752395036964799, "children": { "process_trajectory": { "total": 127.89304165903332, "count": 63869, "self": 127.68342941103356, "children": { "RLTrainer._checkpoint": { "total": 0.20961224799975753, "count": 2, "self": 0.20961224799975753 } } }, "_update_policy": { "total": 492.3972307130032, "count": 453, "self": 288.0036416170144, "children": { "TorchPPOOptimizer.update": { "total": 204.39358909598877, "count": 22782, "self": 204.39358909598877 } } } } } } }, "trainer_threads": { "total": 9.440000212634914e-07, "count": 1, "self": 9.440000212634914e-07 }, "TrainerController._save_models": { "total": 0.08653408600002876, "count": 1, "self": 0.0013635630002681864, "children": { "RLTrainer._checkpoint": { "total": 0.08517052299976058, "count": 1, "self": 0.08517052299976058 } } } } } } }