{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.46052098274230957, "min": 0.4556925296783447, "max": 1.375872015953064, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13822.998046875, "min": 13736.3955078125, "max": 41738.453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989917.0, "min": 29943.0, "max": 989917.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989917.0, "min": 29943.0, "max": 989917.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3869880437850952, "min": -0.08980657160282135, "max": 0.44592928886413574, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 105.64773559570312, "min": -21.553577423095703, "max": 120.18412017822266, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025000564754009247, "min": -0.24214273691177368, "max": 0.4901202619075775, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.8251543045043945, "min": -63.925682067871094, "max": 116.15850067138672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0663434009352285, "min": 0.06567859809130074, "max": 0.07300347870650946, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9951510140284275, "min": 0.495572337429454, "max": 1.0670845753116094, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014461796472864484, "min": 0.000449757067745248, "max": 0.028400232270600487, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21692694709296725, "min": 0.005846841880688224, "max": 0.39760325178840683, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.587597470833334e-06, "min": 7.587597470833334e-06, "max": 0.0002952333015889, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011381396206250001, "min": 0.00011381396206250001, "max": 0.0036327076890974993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252916666666669, "min": 0.10252916666666669, "max": 0.19841109999999998, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5379375000000002, "min": 1.3888776999999999, "max": 2.6109025000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026266375000000004, "min": 0.00026266375000000004, "max": 0.00984126889, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00393995625, "min": 0.00393995625, "max": 0.12110915975, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01358786877244711, "min": 0.012031792663037777, "max": 0.5906277298927307, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20381803810596466, "min": 0.16844509541988373, "max": 4.13439416885376, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 438.1095890410959, "min": 389.5810810810811, "max": 997.65625, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31982.0, "min": 16742.0, "max": 33144.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2878355937053079, "min": -0.9360500497277826, "max": 1.450041073234114, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 94.01199834048748, "min": -30.67520171403885, "max": 105.85299834609032, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2878355937053079, "min": -0.9360500497277826, "max": 1.450041073234114, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 94.01199834048748, "min": -30.67520171403885, "max": 105.85299834609032, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06195109477745089, "min": 0.056850596142483056, "max": 12.346458321108537, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.5224299187539145, "min": 3.7890240466222167, "max": 209.88979145884514, "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": "1691326073", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1691328440" }, "total": 2367.0039597940004, "count": 1, "self": 0.8608214460018644, "children": { "run_training.setup": { "total": 0.038731863999601046, "count": 1, "self": 0.038731863999601046 }, "TrainerController.start_learning": { "total": 2366.104406483999, "count": 1, "self": 1.738763882771309, "children": { "TrainerController._reset_env": { "total": 4.084892652000235, "count": 1, "self": 4.084892652000235 }, "TrainerController.advance": { "total": 2360.1845898242273, "count": 63653, "self": 1.7514304052110674, "children": { "env_step": { "total": 1675.9385229140753, "count": 63653, "self": 1549.426175809932, "children": { "SubprocessEnvManager._take_step": { "total": 125.49498821722136, "count": 63653, "self": 5.345520142279383, "children": { "TorchPolicy.evaluate": { "total": 120.14946807494198, "count": 62546, "self": 120.14946807494198 } } }, "workers": { "total": 1.0173588869220112, "count": 63653, "self": 0.0, "children": { "worker_root": { "total": 2360.1723776809395, "count": 63653, "is_parallel": true, "self": 942.7680041159674, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021283129999574157, "count": 1, "is_parallel": true, "self": 0.0006300890008787974, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014982239990786184, "count": 8, "is_parallel": true, "self": 0.0014982239990786184 } } }, "UnityEnvironment.step": { "total": 0.05349314300019614, "count": 1, "is_parallel": true, "self": 0.0005902840002818266, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005526309996639611, "count": 1, "is_parallel": true, "self": 0.0005526309996639611 }, "communicator.exchange": { "total": 0.050413769999977376, "count": 1, "is_parallel": true, "self": 0.050413769999977376 }, "steps_from_proto": { "total": 0.001936458000272978, "count": 1, "is_parallel": true, "self": 0.00043729400022129994, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014991640000516782, "count": 8, "is_parallel": true, "self": 0.0014991640000516782 } } } } } } }, "UnityEnvironment.step": { "total": 1417.404373564972, "count": 63652, "is_parallel": true, "self": 36.41407451982286, "children": { "UnityEnvironment._generate_step_input": { "total": 25.91797023122217, "count": 63652, "is_parallel": true, "self": 25.91797023122217 }, "communicator.exchange": { "total": 1238.1055702790482, "count": 63652, "is_parallel": true, "self": 1238.1055702790482 }, "steps_from_proto": { "total": 116.96675853487886, "count": 63652, "is_parallel": true, "self": 23.951814881130304, "children": { "_process_rank_one_or_two_observation": { "total": 93.01494365374856, "count": 509216, "is_parallel": true, "self": 93.01494365374856 } } } } } } } } } } }, "trainer_advance": { "total": 682.4946365049409, "count": 63653, "self": 3.1594438299262038, "children": { "process_trajectory": { "total": 119.51403229803054, "count": 63653, "self": 119.29432880103013, "children": { "RLTrainer._checkpoint": { "total": 0.2197034970004097, "count": 2, "self": 0.2197034970004097 } } }, "_update_policy": { "total": 559.8211603769842, "count": 455, "self": 368.4199727180021, "children": { "TorchPPOOptimizer.update": { "total": 191.40118765898205, "count": 22770, "self": 191.40118765898205 } } } } } } }, "trainer_threads": { "total": 9.350005711894482e-07, "count": 1, "self": 9.350005711894482e-07 }, "TrainerController._save_models": { "total": 0.09615918999952555, "count": 1, "self": 0.001408516000083182, "children": { "RLTrainer._checkpoint": { "total": 0.09475067399944237, "count": 1, "self": 0.09475067399944237 } } } } } } }