{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.34532061219215393, "min": 0.34532061219215393, "max": 1.4906738996505737, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10398.2939453125, "min": 10398.2939453125, "max": 45221.08203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989912.0, "min": 29952.0, "max": 989912.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989912.0, "min": 29952.0, "max": 989912.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4758380055427551, "min": -0.10605107247829437, "max": 0.5180547833442688, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.90377807617188, "min": -25.558307647705078, "max": 141.94700622558594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.026432638987898827, "min": -0.017776384949684143, "max": 0.4445474445819855, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.2161102294921875, "min": -4.692965507507324, "max": 105.35774230957031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06507273791413312, "min": 0.06507273791413312, "max": 0.0745755755883532, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9110183307978637, "min": 0.4980434241410928, "max": 1.118633633825298, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013044417798699302, "min": 0.0005549730996706317, "max": 0.01350309825405323, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18262184918179022, "min": 0.00665967719604758, "max": 0.19984505541608943, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.376497541199999e-06, "min": 7.376497541199999e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010327096557679999, "min": 0.00010327096557679999, "max": 0.003507107330964299, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024588, "min": 0.1024588, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344232000000001, "min": 1.3886848, "max": 2.5690357000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025563412000000003, "min": 0.00025563412000000003, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00357887768, "min": 0.00357887768, "max": 0.11692666643, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015565258450806141, "min": 0.015202716924250126, "max": 0.5831053853034973, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21791361272335052, "min": 0.21791361272335052, "max": 4.081737518310547, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 381.5064935064935, "min": 381.5064935064935, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29376.0, "min": 15984.0, "max": 32307.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5145688123710743, "min": -1.0000000521540642, "max": 1.5217612657335498, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 116.62179855257273, "min": -29.959601648151875, "max": 117.09899815917015, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5145688123710743, "min": -1.0000000521540642, "max": 1.5217612657335498, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 116.62179855257273, "min": -29.959601648151875, "max": 117.09899815917015, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06226226219653406, "min": 0.06144746692136116, "max": 12.00093124434352, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.794194189133123, "min": 4.6619494529441, "max": 192.0148999094963, "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": "1687796951", "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": "1687799886" }, "total": 2934.932891263, "count": 1, "self": 0.5816250030002266, "children": { "run_training.setup": { "total": 0.0687335560005522, "count": 1, "self": 0.0687335560005522 }, "TrainerController.start_learning": { "total": 2934.282532703999, "count": 1, "self": 2.3173512541552554, "children": { "TrainerController._reset_env": { "total": 5.530187194000064, "count": 1, "self": 5.530187194000064 }, "TrainerController.advance": { "total": 2926.3231509768448, "count": 63643, "self": 2.235736513867778, "children": { "env_step": { "total": 2143.1453061821458, "count": 63643, "self": 1975.720408188089, "children": { "SubprocessEnvManager._take_step": { "total": 166.0922380209031, "count": 63643, "self": 6.811183217081634, "children": { "TorchPolicy.evaluate": { "total": 159.28105480382146, "count": 62547, "self": 159.28105480382146 } } }, "workers": { "total": 1.332659973153568, "count": 63643, "self": 0.0, "children": { "worker_root": { "total": 2926.513843310099, "count": 63643, "is_parallel": true, "self": 1118.8510602640754, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0032514599997739424, "count": 1, "is_parallel": true, "self": 0.0009860729996944428, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022653870000794996, "count": 8, "is_parallel": true, "self": 0.0022653870000794996 } } }, "UnityEnvironment.step": { "total": 0.06216885199955868, "count": 1, "is_parallel": true, "self": 0.0006490199994004797, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005780720002803719, "count": 1, "is_parallel": true, "self": 0.0005780720002803719 }, "communicator.exchange": { "total": 0.058728039000016, "count": 1, "is_parallel": true, "self": 0.058728039000016 }, "steps_from_proto": { "total": 0.0022137209998618346, "count": 1, "is_parallel": true, "self": 0.00044049799907952547, "children": { "_process_rank_one_or_two_observation": { "total": 0.001773223000782309, "count": 8, "is_parallel": true, "self": 0.001773223000782309 } } } } } } }, "UnityEnvironment.step": { "total": 1807.6627830460238, "count": 63642, "is_parallel": true, "self": 43.66315824806679, "children": { "UnityEnvironment._generate_step_input": { "total": 30.792730295089314, "count": 63642, "is_parallel": true, "self": 30.792730295089314 }, "communicator.exchange": { "total": 1592.6656287148744, "count": 63642, "is_parallel": true, "self": 1592.6656287148744 }, "steps_from_proto": { "total": 140.54126578799332, "count": 63642, "is_parallel": true, "self": 29.562178636692806, "children": { "_process_rank_one_or_two_observation": { "total": 110.97908715130052, "count": 509136, "is_parallel": true, "self": 110.97908715130052 } } } } } } } } } } }, "trainer_advance": { "total": 780.9421082808312, "count": 63643, "self": 4.084163923665983, "children": { "process_trajectory": { "total": 142.34250173115743, "count": 63643, "self": 142.03727647515643, "children": { "RLTrainer._checkpoint": { "total": 0.3052252560009947, "count": 2, "self": 0.3052252560009947 } } }, "_update_policy": { "total": 634.5154426260078, "count": 451, "self": 403.56800138111157, "children": { "TorchPPOOptimizer.update": { "total": 230.94744124489625, "count": 22824, "self": 230.94744124489625 } } } } } } }, "trainer_threads": { "total": 1.3779990695184097e-06, "count": 1, "self": 1.3779990695184097e-06 }, "TrainerController._save_models": { "total": 0.1118419009999343, "count": 1, "self": 0.0016051549991971115, "children": { "RLTrainer._checkpoint": { "total": 0.11023674600073718, "count": 1, "self": 0.11023674600073718 } } } } } } }