{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.06956992298364639, "min": 0.06331828981637955, "max": 1.3611760139465332, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 2083.75830078125, "min": 1900.5618896484375, "max": 41292.63671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0975259318947792, "min": -0.11206963658332825, "max": 0.09031946957111359, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -23.40622329711914, "min": -26.896713256835938, "max": 21.40571403503418, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.50194251537323, "min": 0.3531442880630493, "max": 0.6273393630981445, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 120.46620178222656, "min": 84.04833984375, "max": 151.18878173828125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07236820341572778, "min": 0.06526623435119909, "max": 0.07359188078858313, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0131548478201888, "min": 0.48975283278175097, "max": 1.0258882720817757, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0015132285421785522, "min": 0.0006999882902581435, "max": 0.017204040102164243, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.02118519959049973, "min": 0.00711750811168622, "max": 0.12042828071514969, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.66297601713571e-06, "min": 7.66297601713571e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010728166423989996, "min": 0.00010728166423989996, "max": 0.0025974871341709997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255429285714286, "min": 0.10255429285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357601, "min": 1.3691136000000002, "max": 2.2329767, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026517385642857135, "min": 0.00026517385642857135, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003712433989999999, "min": 0.003712433989999999, "max": 0.0865963171, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.5087481141090393, "min": 0.28730979561805725, "max": 0.8594092130661011, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 7.122473239898682, "min": 3.160407781600952, "max": 7.39610481262207, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 995.1724137931035, "min": 945.939393939394, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28860.0, "min": 15984.0, "max": 33071.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9242357654230935, "min": -1.0000000521540642, "max": -0.7100710205493435, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -25.87860143184662, "min": -32.000001668930054, "max": -16.000000834465027, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9242357654230935, "min": -1.0000000521540642, "max": -0.7100710205493435, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -25.87860143184662, "min": -32.000001668930054, "max": -16.000000834465027, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 4.991433570352716, "min": 2.7793137894736395, "max": 16.823024846613407, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 139.76013996987604, "min": 50.02764821052551, "max": 269.1683975458145, "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": "1676603380", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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=PyramidsTraining --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1676605598" }, "total": 2217.638688178, "count": 1, "self": 0.48486796499992124, "children": { "run_training.setup": { "total": 0.11891361400000733, "count": 1, "self": 0.11891361400000733 }, "TrainerController.start_learning": { "total": 2217.034906599, "count": 1, "self": 1.3785352650124878, "children": { "TrainerController._reset_env": { "total": 6.119136893000018, "count": 1, "self": 6.119136893000018 }, "TrainerController.advance": { "total": 2209.4465158619873, "count": 62919, "self": 1.4308338529767752, "children": { "env_step": { "total": 1453.6860009170507, "count": 62919, "self": 1333.4902124971009, "children": { "SubprocessEnvManager._take_step": { "total": 119.33117292899578, "count": 62919, "self": 4.985385625955246, "children": { "TorchPolicy.evaluate": { "total": 114.34578730304054, "count": 62567, "self": 38.31499391210639, "children": { "TorchPolicy.sample_actions": { "total": 76.03079339093415, "count": 62567, "self": 76.03079339093415 } } } } }, "workers": { "total": 0.8646154909539518, "count": 62919, "self": 0.0, "children": { "worker_root": { "total": 2211.903295891001, "count": 62919, "is_parallel": true, "self": 998.3600683659979, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002115357999969092, "count": 1, "is_parallel": true, "self": 0.0006941549999055496, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014212030000635423, "count": 8, "is_parallel": true, "self": 0.0014212030000635423 } } }, "UnityEnvironment.step": { "total": 0.050158763000013096, "count": 1, "is_parallel": true, "self": 0.0005913699999382516, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005019870000069204, "count": 1, "is_parallel": true, "self": 0.0005019870000069204 }, "communicator.exchange": { "total": 0.047330221000038364, "count": 1, "is_parallel": true, "self": 0.047330221000038364 }, "steps_from_proto": { "total": 0.0017351850000295599, "count": 1, "is_parallel": true, "self": 0.00042755000004035537, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013076349999892045, "count": 8, "is_parallel": true, "self": 0.0013076349999892045 } } } } } } }, "UnityEnvironment.step": { "total": 1213.5432275250032, "count": 62918, "is_parallel": true, "self": 32.23610767995956, "children": { "UnityEnvironment._generate_step_input": { "total": 25.137728574000448, "count": 62918, "is_parallel": true, "self": 25.137728574000448 }, "communicator.exchange": { "total": 1046.9599175840467, "count": 62918, "is_parallel": true, "self": 1046.9599175840467 }, "steps_from_proto": { "total": 109.20947368699649, "count": 62918, "is_parallel": true, "self": 24.41791931222781, "children": { "_process_rank_one_or_two_observation": { "total": 84.79155437476868, "count": 503344, "is_parallel": true, "self": 84.79155437476868 } } } } } } } } } } }, "trainer_advance": { "total": 754.3296810919599, "count": 62919, "self": 2.2504133220141966, "children": { "process_trajectory": { "total": 175.27457195894567, "count": 62919, "self": 175.0833769429455, "children": { "RLTrainer._checkpoint": { "total": 0.1911950160001652, "count": 2, "self": 0.1911950160001652 } } }, "_update_policy": { "total": 576.804695811, "count": 411, "self": 223.0996654839845, "children": { "TorchPPOOptimizer.update": { "total": 353.7050303270155, "count": 22929, "self": 353.7050303270155 } } } } } } }, "trainer_threads": { "total": 9.260002116207033e-07, "count": 1, "self": 9.260002116207033e-07 }, "TrainerController._save_models": { "total": 0.09071765299995604, "count": 1, "self": 0.0015885689999777242, "children": { "RLTrainer._checkpoint": { "total": 0.08912908399997832, "count": 1, "self": 0.08912908399997832 } } } } } } }