{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.11211054027080536, "min": 0.10437927395105362, "max": 1.577974796295166, "count": 200 }, "Pyramids.Policy.Entropy.sum": { "value": 1110.3427734375, "min": 1021.8394775390625, "max": 16158.4619140625, "count": 200 }, "Pyramids.Step.mean": { "value": 1999875.0, "min": 9984.0, "max": 1999875.0, "count": 200 }, "Pyramids.Step.sum": { "value": 1999875.0, "min": 9984.0, "max": 1999875.0, "count": 200 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05197207257151604, "min": -0.10697302222251892, "max": -0.009336870163679123, "count": 200 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -4.209737777709961, "min": -8.664814949035645, "max": -0.7469496130943298, "count": 200 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 1.4934475421905518, "min": 0.45394232869148254, "max": 1.5945155620574951, "count": 200 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 120.96925354003906, "min": 35.407501220703125, "max": 129.15576171875, "count": 200 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07237765926014011, "min": 0.06081282791565172, "max": 0.07969601967865053, "count": 200 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.3618882963007006, "min": 0.14916623805765994, "max": 0.39848009839325266, "count": 200 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00882357942367283, "min": 0.001527048253360679, "max": 0.09856268196385462, "count": 200 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.04411789711836415, "min": 0.0071149989856054, "max": 0.19712536392770924, "count": 200 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.498297500900062e-07, "min": 7.498297500900062e-07, "max": 0.00029907840030719997, "count": 200 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.749148750450031e-06, "min": 3.749148750450031e-06, "max": 0.00140631168122945, "count": 200 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10024991000000003, "min": 0.10024991000000003, "max": 0.1996928, "count": 200 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.5012495500000002, "min": 0.3985856000000001, "max": 0.96877055, "count": 200 }, "Pyramids.Policy.Beta.mean": { "value": 3.496600900000021e-05, "min": 3.496600900000021e-05, "max": 0.00996931072, "count": 200 }, "Pyramids.Policy.Beta.sum": { "value": 0.00017483004500000104, "min": 0.00017483004500000104, "max": 0.046880177945000004, "count": 200 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.7244455218315125, "min": 0.6063039898872375, "max": 0.9765970706939697, "count": 200 }, "Pyramids.Losses.RNDLoss.sum": { "value": 3.622227668762207, "min": 1.4746968746185303, "max": 4.058317184448242, "count": 200 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 916.0, "min": 667.0, "max": 999.0, "count": 197 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 11908.0, "min": 667.0, "max": 15984.0, "count": 197 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.4549538968847348, "min": -1.0000000521540642, "max": 1.3330000191926956, "count": 197 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -5.914400659501553, "min": -16.000000834465027, "max": 1.4721996784210205, "count": 197 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.4549538968847348, "min": -1.0000000521540642, "max": 1.3330000191926956, "count": 197 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -5.914400659501553, "min": -16.000000834465027, "max": 1.4721996784210205, "count": 197 }, "Pyramids.Policy.RndReward.mean": { "value": 12.666740596294403, "min": 9.22929909825325, "max": 25.736984878778458, "count": 197 }, "Pyramids.Policy.RndReward.sum": { "value": 164.66762775182724, "min": 9.22929909825325, "max": 411.7917580604553, "count": 197 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688614286", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1688618735" }, "total": 4449.416645535, "count": 1, "self": 0.5417612119990736, "children": { "run_training.setup": { "total": 0.04669272599994656, "count": 1, "self": 0.04669272599994656 }, "TrainerController.start_learning": { "total": 4448.828191597, "count": 1, "self": 3.594500760970732, "children": { "TrainerController._reset_env": { "total": 4.704707150000104, "count": 1, "self": 4.704707150000104 }, "TrainerController.advance": { "total": 4440.459955096028, "count": 126654, "self": 3.7311828959327613, "children": { "env_step": { "total": 3008.8068601269124, "count": 126654, "self": 2733.304379934815, "children": { "SubprocessEnvManager._take_step": { "total": 273.2025281229546, "count": 126654, "self": 11.415960402927567, "children": { "TorchPolicy.evaluate": { "total": 261.78656772002705, "count": 125051, "self": 261.78656772002705 } } }, "workers": { "total": 2.299952069142364, "count": 126654, "self": 0.0, "children": { "worker_root": { "total": 4436.794861562939, "count": 126654, "is_parallel": true, "self": 1982.681795018997, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00726297500000328, "count": 1, "is_parallel": true, "self": 0.0057260560001850536, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015369189998182264, "count": 8, "is_parallel": true, "self": 0.0015369189998182264 } } }, "UnityEnvironment.step": { "total": 0.05525759399984054, "count": 1, "is_parallel": true, "self": 0.0006821769998168747, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005257160000837757, "count": 1, "is_parallel": true, "self": 0.0005257160000837757 }, "communicator.exchange": { "total": 0.04979021700000885, "count": 1, "is_parallel": true, "self": 0.04979021700000885 }, "steps_from_proto": { "total": 0.004259483999931035, "count": 1, "is_parallel": true, "self": 0.00045026899965705525, "children": { "_process_rank_one_or_two_observation": { "total": 0.00380921500027398, "count": 8, "is_parallel": true, "self": 0.00380921500027398 } } } } } } }, "UnityEnvironment.step": { "total": 2454.1130665439423, "count": 126653, "is_parallel": true, "self": 79.46362502206784, "children": { "UnityEnvironment._generate_step_input": { "total": 51.10031400495973, "count": 126653, "is_parallel": true, "self": 51.10031400495973 }, "communicator.exchange": { "total": 2086.1441328030096, "count": 126653, "is_parallel": true, "self": 2086.1441328030096 }, "steps_from_proto": { "total": 237.40499471390513, "count": 126653, "is_parallel": true, "self": 47.60021024569414, "children": { "_process_rank_one_or_two_observation": { "total": 189.80478446821098, "count": 1013224, "is_parallel": true, "self": 189.80478446821098 } } } } } } } } } } }, "trainer_advance": { "total": 1427.9219120731832, "count": 126654, "self": 7.376676462175283, "children": { "process_trajectory": { "total": 244.58542896601148, "count": 126654, "self": 244.13669510001046, "children": { "RLTrainer._checkpoint": { "total": 0.44873386600102094, "count": 4, "self": 0.44873386600102094 } } }, "_update_policy": { "total": 1175.9598066449964, "count": 921, "self": 761.7648807160115, "children": { "TorchPPOOptimizer.update": { "total": 414.19492592898496, "count": 45459, "self": 414.19492592898496 } } } } } } }, "trainer_threads": { "total": 9.680006769485772e-07, "count": 1, "self": 9.680006769485772e-07 }, "TrainerController._save_models": { "total": 0.06902762200024881, "count": 1, "self": 0.0005604360003417241, "children": { "RLTrainer._checkpoint": { "total": 0.06846718599990709, "count": 1, "self": 0.06846718599990709 } } } } } } }