{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2968568205833435, "min": 0.2968568205833435, "max": 1.3924744129180908, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9014.9482421875, "min": 9014.9482421875, "max": 42242.10546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989997.0, "min": 29952.0, "max": 989997.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989997.0, "min": 29952.0, "max": 989997.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6367574334144592, "min": -0.07481157034635544, "max": 0.7033754587173462, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 185.93316650390625, "min": -18.104400634765625, "max": 200.46200561523438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.008130650036036968, "min": -0.08959388732910156, "max": 0.4435449242591858, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.374149799346924, "min": -23.47359848022461, "max": 105.12014770507812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06918248030543261, "min": 0.06539824031887209, "max": 0.07435832993360236, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9685547242760566, "min": 0.5205083095352165, "max": 1.0509640484427412, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018703448938265182, "min": 0.0015976215277064437, "max": 0.02702211440313889, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.26184828513571257, "min": 0.020769079860183767, "max": 0.37830960164394445, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.669190300778567e-06, "min": 7.669190300778567e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010736866421089994, "min": 0.00010736866421089994, "max": 0.0037577323474225995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255636428571427, "min": 0.10255636428571427, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357890999999998, "min": 1.3886848, "max": 2.6525773999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000265380792142857, "min": 0.000265380792142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003715331089999998, "min": 0.003715331089999998, "max": 0.12527248226000004, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01387251727283001, "min": 0.012911198660731316, "max": 0.5392094850540161, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19421523809432983, "min": 0.18075677752494812, "max": 3.7744665145874023, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 272.7962962962963, "min": 272.7962962962963, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29462.0, "min": 15984.0, "max": 32860.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7272036875839587, "min": -1.0000000521540642, "max": 1.7272036875839587, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 186.53799825906754, "min": -26.88620176911354, "max": 186.53799825906754, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7272036875839587, "min": -1.0000000521540642, "max": 1.7272036875839587, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 186.53799825906754, "min": -26.88620176911354, "max": 186.53799825906754, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0390021382562635, "min": 0.0390021382562635, "max": 11.082654763013124, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.212230931676459, "min": 3.815102604603453, "max": 177.32247620821, "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": "1680099929", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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=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": "1680102196" }, "total": 2266.850120855, "count": 1, "self": 0.48971570699995937, "children": { "run_training.setup": { "total": 0.18394966400001067, "count": 1, "self": 0.18394966400001067 }, "TrainerController.start_learning": { "total": 2266.176455484, "count": 1, "self": 1.3887346680139672, "children": { "TrainerController._reset_env": { "total": 6.085080806000178, "count": 1, "self": 6.085080806000178 }, "TrainerController.advance": { "total": 2258.608458625986, "count": 64152, "self": 1.4380654299366142, "children": { "env_step": { "total": 1628.393942739994, "count": 64152, "self": 1520.9863970889971, "children": { "SubprocessEnvManager._take_step": { "total": 106.585707780961, "count": 64152, "self": 4.662254750953707, "children": { "TorchPolicy.evaluate": { "total": 101.9234530300073, "count": 62578, "self": 101.9234530300073 } } }, "workers": { "total": 0.8218378700357789, "count": 64152, "self": 0.0, "children": { "worker_root": { "total": 2261.309567956017, "count": 64152, "is_parallel": true, "self": 856.3136416849711, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017184319999614672, "count": 1, "is_parallel": true, "self": 0.0005352180000954831, "children": { "_process_rank_one_or_two_observation": { "total": 0.001183213999865984, "count": 8, "is_parallel": true, "self": 0.001183213999865984 } } }, "UnityEnvironment.step": { "total": 0.051468656999986706, "count": 1, "is_parallel": true, "self": 0.000513708000198676, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000503327999922476, "count": 1, "is_parallel": true, "self": 0.000503327999922476 }, "communicator.exchange": { "total": 0.0488665759999094, "count": 1, "is_parallel": true, "self": 0.0488665759999094 }, "steps_from_proto": { "total": 0.0015850449999561533, "count": 1, "is_parallel": true, "self": 0.0003778400000555848, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012072049999005685, "count": 8, "is_parallel": true, "self": 0.0012072049999005685 } } } } } } }, "UnityEnvironment.step": { "total": 1404.9959262710458, "count": 64151, "is_parallel": true, "self": 31.632712491978054, "children": { "UnityEnvironment._generate_step_input": { "total": 22.554929432995095, "count": 64151, "is_parallel": true, "self": 22.554929432995095 }, "communicator.exchange": { "total": 1258.2538356030682, "count": 64151, "is_parallel": true, "self": 1258.2538356030682 }, "steps_from_proto": { "total": 92.55444874300451, "count": 64151, "is_parallel": true, "self": 19.671999831810353, "children": { "_process_rank_one_or_two_observation": { "total": 72.88244891119416, "count": 513208, "is_parallel": true, "self": 72.88244891119416 } } } } } } } } } } }, "trainer_advance": { "total": 628.7764504560555, "count": 64152, "self": 2.6290804510726957, "children": { "process_trajectory": { "total": 118.76069937798388, "count": 64152, "self": 118.55940100598377, "children": { "RLTrainer._checkpoint": { "total": 0.20129837200011025, "count": 2, "self": 0.20129837200011025 } } }, "_update_policy": { "total": 507.3866706269989, "count": 458, "self": 323.72726668697896, "children": { "TorchPPOOptimizer.update": { "total": 183.65940394001996, "count": 22803, "self": 183.65940394001996 } } } } } } }, "trainer_threads": { "total": 1.0050002856587525e-06, "count": 1, "self": 1.0050002856587525e-06 }, "TrainerController._save_models": { "total": 0.09418037899968112, "count": 1, "self": 0.0013571389995377103, "children": { "RLTrainer._checkpoint": { "total": 0.09282324000014341, "count": 1, "self": 0.09282324000014341 } } } } } } }