{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1704377681016922, "min": 0.16250012814998627, "max": 1.3789162635803223, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5061.31982421875, "min": 4864.60400390625, "max": 41830.8046875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999914.0, "min": 29952.0, "max": 2999914.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999914.0, "min": 29952.0, "max": 2999914.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7902837991714478, "min": -0.09778378903865814, "max": 0.8584803938865662, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 237.87542724609375, "min": -23.565893173217773, "max": 262.69500732421875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00298650492914021, "min": -0.018346533179283142, "max": 0.24226222932338715, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.898938000202179, "min": -5.320494651794434, "max": 58.14293670654297, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0656459979031102, "min": 0.0640618006432369, "max": 0.07418233807034352, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9190439706435427, "min": 0.4868394951367866, "max": 1.112735071055153, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014464565969925996, "min": 6.014493335350987e-05, "max": 0.017031274515284675, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20250392357896393, "min": 0.0007818841335956283, "max": 0.24928042040133447, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5315923466452327e-06, "min": 1.5315923466452327e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.144229285303326e-05, "min": 2.144229285303326e-05, "max": 0.003969168476943867, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051049761904762, "min": 0.10051049761904762, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071469666666667, "min": 1.3962282666666668, "max": 2.7375194333333335, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.099871214285698e-05, "min": 6.099871214285698e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008539819699999977, "min": 0.0008539819699999977, "max": 0.13231330772, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006842241622507572, "min": 0.006842241622507572, "max": 0.45617565512657166, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09579138457775116, "min": 0.09579138457775116, "max": 3.1932296752929688, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 218.77037037037036, "min": 205.33812949640287, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29534.0, "min": 15984.0, "max": 32976.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7664088795582453, "min": -1.0000000521540642, "max": 1.7946618575629572, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 238.46519874036312, "min": -29.98700162023306, "max": 255.99759805202484, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7664088795582453, "min": -1.0000000521540642, "max": 1.7946618575629572, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 238.46519874036312, "min": -29.98700162023306, "max": 255.99759805202484, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0155968772913588, "min": 0.015450548466813215, "max": 8.832182018086314, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.105578434333438, "min": 2.105578434333438, "max": 141.31491228938103, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1673979155", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.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": "1673985886" }, "total": 6731.185879846999, "count": 1, "self": 0.4362290599992775, "children": { "run_training.setup": { "total": 0.11607115999959206, "count": 1, "self": 0.11607115999959206 }, "TrainerController.start_learning": { "total": 6730.6335796270005, "count": 1, "self": 3.603178385767933, "children": { "TrainerController._reset_env": { "total": 6.405750881999666, "count": 1, "self": 6.405750881999666 }, "TrainerController.advance": { "total": 6720.532759976234, "count": 194738, "self": 3.622378233094423, "children": { "env_step": { "total": 4727.929942035064, "count": 194738, "self": 4427.488266751005, "children": { "SubprocessEnvManager._take_step": { "total": 298.2716086270757, "count": 194738, "self": 12.487329158991088, "children": { "TorchPolicy.evaluate": { "total": 285.7842794680846, "count": 187547, "self": 96.50915453912148, "children": { "TorchPolicy.sample_actions": { "total": 189.27512492896312, "count": 187547, "self": 189.27512492896312 } } } } }, "workers": { "total": 2.1700666569840905, "count": 194738, "self": 0.0, "children": { "worker_root": { "total": 6717.929572420756, "count": 194738, "is_parallel": true, "self": 2577.9597060974784, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016657129999657627, "count": 1, "is_parallel": true, "self": 0.0005343929997252417, "children": { "_process_rank_one_or_two_observation": { "total": 0.001131320000240521, "count": 8, "is_parallel": true, "self": 0.001131320000240521 } } }, "UnityEnvironment.step": { "total": 0.044550435000019206, "count": 1, "is_parallel": true, "self": 0.00046901699988666223, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004629760005627759, "count": 1, "is_parallel": true, "self": 0.0004629760005627759 }, "communicator.exchange": { "total": 0.04197596399990289, "count": 1, "is_parallel": true, "self": 0.04197596399990289 }, "steps_from_proto": { "total": 0.0016424779996668804, "count": 1, "is_parallel": true, "self": 0.00040788099886412965, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012345970008027507, "count": 8, "is_parallel": true, "self": 0.0012345970008027507 } } } } } } }, "UnityEnvironment.step": { "total": 4139.9698663232775, "count": 194737, "is_parallel": true, "self": 83.69388864580469, "children": { "UnityEnvironment._generate_step_input": { "total": 66.25068691022989, "count": 194737, "is_parallel": true, "self": 66.25068691022989 }, "communicator.exchange": { "total": 3691.435993178892, "count": 194737, "is_parallel": true, "self": 3691.435993178892 }, "steps_from_proto": { "total": 298.58929758835075, "count": 194737, "is_parallel": true, "self": 64.67071543008478, "children": { "_process_rank_one_or_two_observation": { "total": 233.91858215826596, "count": 1557896, "is_parallel": true, "self": 233.91858215826596 } } } } } } } } } } }, "trainer_advance": { "total": 1988.9804397080752, "count": 194738, "self": 6.85351151818486, "children": { "process_trajectory": { "total": 439.5669318208784, "count": 194738, "self": 438.98961023787797, "children": { "RLTrainer._checkpoint": { "total": 0.5773215830004119, "count": 6, "self": 0.5773215830004119 } } }, "_update_policy": { "total": 1542.559996369012, "count": 1391, "self": 590.9275996289753, "children": { "TorchPPOOptimizer.update": { "total": 951.6323967400367, "count": 68307, "self": 951.6323967400367 } } } } } } }, "trainer_threads": { "total": 1.5519999578827992e-06, "count": 1, "self": 1.5519999578827992e-06 }, "TrainerController._save_models": { "total": 0.0918888309988688, "count": 1, "self": 0.0015667959978600265, "children": { "RLTrainer._checkpoint": { "total": 0.09032203500100877, "count": 1, "self": 0.09032203500100877 } } } } } } }