{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3684692680835724, "min": 0.3578437566757202, "max": 1.4210155010223389, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11006.9140625, "min": 10729.5869140625, "max": 43107.92578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989895.0, "min": 29995.0, "max": 989895.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989895.0, "min": 29995.0, "max": 989895.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.38654443621635437, "min": -0.096100352704525, "max": 0.5439761281013489, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 103.20736694335938, "min": -23.064085006713867, "max": 151.7693328857422, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01998446322977543, "min": 0.006764187011867762, "max": 0.3527693450450897, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.335851669311523, "min": 1.6842825412750244, "max": 83.9591064453125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06792522436345001, "min": 0.06334115784210595, "max": 0.07233228066972656, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9509531410883002, "min": 0.49443029696570073, "max": 1.0286479569040239, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015161994724740651, "min": 0.0004526815782604029, "max": 0.015495821125213518, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2122679261463691, "min": 0.0063375420956456405, "max": 0.21694149575298927, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.2550190102642846e-06, "min": 7.2550190102642846e-06, "max": 0.0002952365587306714, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010157026614369998, "min": 0.00010157026614369998, "max": 0.003633586988804399, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241830714285716, "min": 0.10241830714285716, "max": 0.1984121857142857, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338563000000002, "min": 1.3888852999999999, "max": 2.6111956, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002515888835714286, "min": 0.0002515888835714286, "max": 0.009841377352857143, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00352224437, "min": 0.00352224437, "max": 0.12113844044, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010798096656799316, "min": 0.010798096656799316, "max": 0.5842085480690002, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15117335319519043, "min": 0.15117335319519043, "max": 4.0894598960876465, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 440.59154929577466, "min": 348.39285714285717, "max": 997.0967741935484, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31282.0, "min": 16538.0, "max": 33982.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3015999758823051, "min": -0.9332516654845207, "max": 1.6112433566027378, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 93.71519826352596, "min": -28.93080163002014, "max": 133.73319859802723, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3015999758823051, "min": -0.9332516654845207, "max": 1.6112433566027378, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 93.71519826352596, "min": -28.93080163002014, "max": 133.73319859802723, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.049021377686383656, "min": 0.03999345808578178, "max": 10.794142111259347, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.529539193419623, "min": 3.2991481129356544, "max": 183.50041589140892, "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": "1706501155", "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=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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706503463" }, "total": 2308.129902916, "count": 1, "self": 0.49170943399985845, "children": { "run_training.setup": { "total": 0.05699374099992838, "count": 1, "self": 0.05699374099992838 }, "TrainerController.start_learning": { "total": 2307.581199741, "count": 1, "self": 1.4317969400326547, "children": { "TrainerController._reset_env": { "total": 3.0447921439999845, "count": 1, "self": 3.0447921439999845 }, "TrainerController.advance": { "total": 2303.016596910967, "count": 63770, "self": 1.601564037933258, "children": { "env_step": { "total": 1664.610752839992, "count": 63770, "self": 1526.5127461119637, "children": { "SubprocessEnvManager._take_step": { "total": 137.18364373304803, "count": 63770, "self": 4.924271198028919, "children": { "TorchPolicy.evaluate": { "total": 132.2593725350191, "count": 62563, "self": 132.2593725350191 } } }, "workers": { "total": 0.9143629949802516, "count": 63770, "self": 0.0, "children": { "worker_root": { "total": 2302.1687234540086, "count": 63770, "is_parallel": true, "self": 902.4272290980675, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004328435999923386, "count": 1, "is_parallel": true, "self": 0.00300995699979012, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013184790001332658, "count": 8, "is_parallel": true, "self": 0.0013184790001332658 } } }, "UnityEnvironment.step": { "total": 0.04856184699997357, "count": 1, "is_parallel": true, "self": 0.0005905759999222937, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000501502000020082, "count": 1, "is_parallel": true, "self": 0.000501502000020082 }, "communicator.exchange": { "total": 0.04582509499994103, "count": 1, "is_parallel": true, "self": 0.04582509499994103 }, "steps_from_proto": { "total": 0.0016446740000901627, "count": 1, "is_parallel": true, "self": 0.00034038699982374965, "children": { "_process_rank_one_or_two_observation": { "total": 0.001304287000266413, "count": 8, "is_parallel": true, "self": 0.001304287000266413 } } } } } } }, "UnityEnvironment.step": { "total": 1399.741494355941, "count": 63769, "is_parallel": true, "self": 36.19557494505602, "children": { "UnityEnvironment._generate_step_input": { "total": 25.36831988095605, "count": 63769, "is_parallel": true, "self": 25.36831988095605 }, "communicator.exchange": { "total": 1234.0900331099735, "count": 63769, "is_parallel": true, "self": 1234.0900331099735 }, "steps_from_proto": { "total": 104.08756641995546, "count": 63769, "is_parallel": true, "self": 21.466564085883192, "children": { "_process_rank_one_or_two_observation": { "total": 82.62100233407227, "count": 510152, "is_parallel": true, "self": 82.62100233407227 } } } } } } } } } } }, "trainer_advance": { "total": 636.804280033042, "count": 63770, "self": 2.9100215810192367, "children": { "process_trajectory": { "total": 133.43294661502375, "count": 63770, "self": 133.2436610020235, "children": { "RLTrainer._checkpoint": { "total": 0.18928561300026558, "count": 2, "self": 0.18928561300026558 } } }, "_update_policy": { "total": 500.461311836999, "count": 457, "self": 297.77852626596996, "children": { "TorchPPOOptimizer.update": { "total": 202.68278557102906, "count": 22821, "self": 202.68278557102906 } } } } } } }, "trainer_threads": { "total": 8.71000338520389e-07, "count": 1, "self": 8.71000338520389e-07 }, "TrainerController._save_models": { "total": 0.08801287500000399, "count": 1, "self": 0.00144073199999184, "children": { "RLTrainer._checkpoint": { "total": 0.08657214300001215, "count": 1, "self": 0.08657214300001215 } } } } } } }